A Simple Framework for Contrastive Learning of Visual Representations

Abstract

This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.

ICML'2020. Code and pretrained models at https://github.com/google-research/simclr

References in corpus (19)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Estimation of Word Representations in Vector Space
• Representation Learning with Contrastive Predictive Coding
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Improved Regularization of Convolutional Neural Networks with Cutout
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Learning deep representations by mutual information estimation and maximization
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Unsupervised Data Augmentation for Consistency Training
• Fine-Grained Visual Classification of Aircraft
• Momentum Contrast for Unsupervised Visual Representation Learning
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Contrastive Multiview Coding
• Large Batch Training of Convolutional Networks
• Large Scale Adversarial Representation Learning
• Some Improvements on Deep Convolutional Neural Network Based Image Classification
• On Mutual Information Maximization for Representation Learning
• A critical analysis of self-supervision, or what we can learn from a single image

Cited by in corpus (1092)

• Learning Transferable Visual Models From Natural Language Supervision
• Transformers in Vision: A Survey
• Bootstrap your own latent: A new approach to self-supervised Learning
• Learning to Prompt for Vision-Language Models
• Improved Baselines with Momentum Contrastive Learning
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Diffusion Models in Vision: A Survey
• Recent advances and clinical applications of deep learning in medical image analysis
• Graph Contrastive Learning with Adaptive Augmentation
• DINOv2: Learning Robust Visual Features without Supervision
• Momentum Contrast for Unsupervised Visual Representation Learning
• BEiT: BERT Pre-Training of Image Transformers
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Graph Contrastive Learning with Augmentations
• Contrastive Representation Learning: A Framework and Review
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• What Makes for Good Views for Contrastive Learning?
• TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Improving Graph Collaborative Filtering with Neighborhood-enriched Contrastive Learning
• Graph Self-Supervised Learning: A Survey
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Knowledge Graph Contrastive Learning for Recommendation
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
• Deep Graph Contrastive Representation Learning
• Exploring Simple Siamese Representation Learning
• Rethinking Pre-training and Self-training
• Contrastive Multi-View Representation Learning on Graphs
• Florence: A New Foundation Model for Computer Vision
• Embodied Intelligence via Learning and Evolution
• Models Genesis
• Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition
• SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation
• Image Quality Assessment using Contrastive Learning
• Self-supervised Co-training for Video Representation Learning
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• An Overview of Deep Semi-Supervised Learning
• Large AI Models in Health Informatics: Applications, Challenges, and the Future
• Towards Out-Of-Distribution Generalization: A Survey
• Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
• An Empirical Study of Remote Sensing Pretraining
• CLEAR: Contrastive Learning for Sentence Representation
• Contrastive Cross-site Learning with Redesigned Net for COVID-19 CT Classification
• Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
• Foundation Models for Time Series Analysis: A Tutorial and Survey
• A survey on Semi-, Self- and Unsupervised Learning for Image Classification
• CURL: Contrastive Unsupervised Representations for Reinforcement Learning
• Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions
• Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review
• Self-Supervised MultiModal Versatile Networks
• Self-supervised representation learning from 12-lead ECG data
• Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging
• Label-Efficient Self-Supervised Federated Learning for Tackling Data Heterogeneity in Medical Imaging
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• A Review-aware Graph Contrastive Learning Framework for Recommendation
• Video Transformers: A Survey
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• TCLR: Temporal Contrastive Learning for Video Representation
• A Survey on Long-Tailed Visual Recognition
• Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
• Twin Contrastive Learning for Online Clustering
• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• Self-Supervised Learning for Videos: A Survey
• DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD classification directly from H&E whole-slide images in colorectal and breast cancer
• Self-supervised Pretraining of Visual Features in the Wild
• SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
• Viral Pneumonia Screening on Chest X-ray Images Using Confidence-Aware Anomaly Detection
• SelfHAR: Improving Human Activity Recognition through Self-training with Unlabeled Data
• Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
• Learning Representation for Clustering via Prototype Scattering and Positive Sampling
• 3D Self-Supervised Methods for Medical Imaging
• Pre-Trained Image Processing Transformer
• The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
• Structure-Preserving Image Super-Resolution
• Disentangling Long and Short-Term Interests for Recommendation
• Semantic Models for the First-stage Retrieval: A Comprehensive Review
• Image Augmentations for GAN Training
• Semantics-Guided Contrastive Network for Zero-Shot Object detection
• A Comprehensive Study of Deep Video Action Recognition
• Supervised Contrastive Learning
• Grammatical Error Correction: A Survey of the State of the Art
• Space-Time Correspondence as a Contrastive Random Walk
• Self-Supervised Learning with Swin Transformers
• Active label cleaning for improved dataset quality under resource constraints
• Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework
• Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series
• CrossCBR: Cross-view Contrastive Learning for Bundle Recommendation
• IMF: Interactive Multimodal Fusion Model for Link Prediction
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works
• CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
• CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification
• Self-Supervised Multisensor Change Detection
• Learning Disentangled Representations in the Imaging Domain
• A Self-Supervised Gait Encoding Approach with Locality-Awareness for 3D Skeleton Based Person Re-Identification
• COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learning
• Outlier Exposure with Confidence Control for Out-of-Distribution Detection
• ContraGAN: Contrastive Learning for Conditional Image Generation
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
• PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
• Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey
• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision
• Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
• What Should Not Be Contrastive in Contrastive Learning
• Learning and Evaluating Representations for Deep One-class Classification
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• Understanding Dimensional Collapse in Contrastive Self-supervised Learning
• Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
• Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labels
• Exploring Deep Neural Networks via Layer-Peeled Model: Minority Collapse in Imbalanced Training
• COCOA: Cross Modality Contrastive Learning for Sensor Data
• HyperNet: Self-Supervised Hyperspectral Spatial-Spectral Feature Understanding Network for Hyperspectral Change Detection
• Deep Learning-Based Human Pose Estimation: A Survey
• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
• Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
• Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning
• What makes instance discrimination good for transfer learning?
• Contrastive Collaborative Filtering for Cold-Start Item Recommendation
• Efficient Self-supervised Vision Transformers for Representation Learning
• Learning Predictive Representations for Deformable Objects Using Contrastive Estimation
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Labelling unlabelled videos from scratch with multi-modal self-supervision
• Memory-augmented Dense Predictive Coding for Video Representation Learning
• Self-supervised deep convolutional neural network for chest X-ray classification
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
• Self-Supervised Representation Learning for Astronomical Images
• Domain Generalization using Causal Matching
• Cooperative learning for multiview analysis
• Subject-Aware Contrastive Learning for Biosignals
• Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Hierarchical Self-supervised Augmented Knowledge Distillation
• Are we done with ImageNet?
• SEED: Self-supervised Distillation For Visual Representation
• Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
• Robust Pre-Training by Adversarial Contrastive Learning
• Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation
• Self-supervised Knowledge Distillation for Few-shot Learning
• GPT-GNN: Generative Pre-Training of Graph Neural Networks
• Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification
• A Framework For Contrastive Self-Supervised Learning And Designing A New Approach
• Contrastive Out-of-Distribution Detection for Pretrained Transformers
• Self-EMD: Self-Supervised Object Detection without ImageNet
• Collaborative Learning for Faster StyleGAN Embedding
• Active, Continual Fine Tuning of Convolutional Neural Networks for Reducing Annotation Efforts
• Self-supervised learning through the eyes of a child
• Decoupling Representation Learning from Reinforcement Learning
• CL4CTR: A Contrastive Learning Framework for CTR Prediction
• Differentially Private Learning Needs Better Features (or Much More Data)
• VoxSRC 2020: The Second VoxCeleb Speaker Recognition Challenge
• Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
• Automated Spatio-Temporal Graph Contrastive Learning
• Self-Supervised Policy Adaptation during Deployment
• Partial success in closing the gap between human and machine vision
• Intriguing Properties of Contrastive Losses
• Unsupervised Feature Learning by Autoencoder and Prototypical Contrastive Learning for Hyperspectral Classification
• AstroCLIP: A Cross-Modal Foundation Model for Galaxies
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective
• Video Representation Learning with Visual Tempo Consistency
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis
• Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction
• BYOL for Audio: Exploring Pre-trained General-purpose Audio Representations
• A Survey of Deep Learning for Scientific Discovery
• I2V-GAN: Unpaired Infrared-to-Visible Video Translation
• Multi-level Second-order Few-shot Learning
• DEPA: Self-Supervised Audio Embedding for Depression Detection
• Are all negatives created equal in contrastive instance discrimination?
• Federated Contrastive Learning for Volumetric Medical Image Segmentation
• Exploring Contrastive Learning in Human Activity Recognition for Healthcare
• CoMIR: Contrastive Multimodal Image Representation for Registration
• Learning Off-Road Terrain Traversability with Self-Supervisions Only
• i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
• Toward Interpretable Sleep Stage Classification Using Cross-Modal Transformers
• MixCo: Mix-up Contrastive Learning for Visual Representation
• Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection
• Contrastive Learning with Adversarial Examples
• Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking
• Automatic Data Augmentation for Generalization in Deep Reinforcement Learning
• MoCo-CXR: MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models
• Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
• An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey
• Unsupervised Deep Representation Learning and Few-Shot Classification of PolSAR Images
• An Overview of Algorithms for Contactless Cardiac Feature Extraction from Radar Signals: Advances and Challenges
• MWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
• Jointly Contrastive Representation Learning on Road Network and Trajectory
• Object DGCNN: 3D Object Detection using Dynamic Graphs
• On Mutual Information in Contrastive Learning for Visual Representations
• Self-supervised Consensus Representation Learning for Attributed Graph
• Trusted Multi-View Classification
• Data-Efficient Reinforcement Learning with Self-Predictive Representations
• Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
• Self-Supervised RF Signal Representation Learning for NextG Signal Classification with Deep Learning
• Predicting What You Already Know Helps: Provable Self-Supervised Learning
• Open-World Semi-Supervised Learning
• ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer
• Unsupervised Contrastive Learning based Transformer for Lung Nodule Detection
• Automated Audio Captioning: An Overview of Recent Progress and New Challenges
• Self-supervised Audiovisual Representation Learning for Remote Sensing Data
• A review of unsupervised learning in astronomy
• Contrastive Learning for Recommender System
• Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation
• Can segmentation models be trained with fully synthetically generated data?
• Multi-level Contrastive Learning Framework for Sequential Recommendation
• Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
• Deep Robust Clustering by Contrastive Learning
• Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval
• A Geometric Analysis of Neural Collapse with Unconstrained Features
• Whitening for Self-Supervised Representation Learning
• FedDG: Federated Domain Generalization on Medical Image Segmentation via Episodic Learning in Continuous Frequency Space
• From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape
• Semantic-Aware Adversarial Training for Reliable Deep Hashing Retrieval
• Bringing Your Own View: Graph Contrastive Learning without Prefabricated Data Augmentations
• Learning Invariance from Generated Variance for Unsupervised Person Re-identification
• TRILLsson: Distilled Universal Paralinguistic Speech Representations
• ReSSL: Relational Self-Supervised Learning with Weak Augmentation
• Self-Supervised Learning Based Domain Adaptation for Robust Speaker Verification
• Reinforcement Learning with Prototypical Representations
• Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
• Representation Learning via Invariant Causal Mechanisms
• Contrastive Knowledge Graph Error Detection
• CGC: Contrastive Graph Clustering for Community Detection and Tracking
• Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation
• Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
• Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity
• Watching the World Go By: Representation Learning from Unlabeled Videos
• Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation
• Robust Domain Misinformation Detection via Multi-modal Feature Alignment
• Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation
• Continual Learning for Generative Retrieval over Dynamic Corpora
• Supervised Contrastive Learning for Product Matching
• Multi-Label Contrastive Learning for Abstract Visual Reasoning
• The Lottery Ticket Hypothesis for Pre-trained BERT Networks
• Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Contrastive Self-supervised Neural Architecture Search
• Contrastive Learning with Stronger Augmentations
• Clustering-friendly Representation Learning via Instance Discrimination and Feature Decorrelation
• Parameter Efficient Multimodal Transformers for Video Representation Learning
• Unsupervised Outlier Detection using Memory and Contrastive Learning
• Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
• Intent-aware Recommendation via Disentangled Graph Contrastive Learning
• Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking
• Understanding self-supervised Learning Dynamics without Contrastive Pairs
• P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
• Understanding Self-supervised Learning with Dual Deep Networks
• Structure-aware Visualization Retrieval
• Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
• SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
• Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction
• UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
• Contrastive Learning of Musical Representations
• Context-self contrastive pretraining for crop type semantic segmentation
• Self-supervised Contrastive Learning of Multi-view Facial Expressions
• Do Different Tracking Tasks Require Different Appearance Models?
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Uncertainty Quantification and Deep Ensembles
• The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
• Contrastive Model Inversion for Data-Free Knowledge Distillation
• Conditional Generation of Medical Images via Disentangled Adversarial Inference
• How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?
• See through Gradients: Image Batch Recovery via GradInversion
• Multi-Format Contrastive Learning of Audio Representations
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• Pair-Level Supervised Contrastive Learning for Natural Language Inference
• CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
• Self-supervised Contrastive Learning for Volcanic Unrest Detection
• MTS-DVGAN: Anomaly Detection in Cyber-Physical Systems using a Dual Variational Generative Adversarial Network
• RepsNet: Combining Vision with Language for Automated Medical Reports
• A Study of the Generalizability of Self-Supervised Representations
• Can Temporal Information Help with Contrastive Self-Supervised Learning?
• Self-supervised Learning for Large-scale Item Recommendations
• MST: Masked Self-Supervised Transformer for Visual Representation
• An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training
• Efficient Personalized Speech Enhancement through Self-Supervised Learning
• Contrastive Learning Inverts the Data Generating Process
• Self-Supervised Relational Reasoning for Representation Learning
• Towards Robust Graph Contrastive Learning
• A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques
• Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation
• Improved Contrastive Divergence Training of Energy Based Models
• Contrastive Learning with Cross-Modal Knowledge Mining for Multimodal Human Activity Recognition
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding
• Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning
• Hierarchical Skeleton Meta-Prototype Contrastive Learning with Hard Skeleton Mining for Unsupervised Person Re-Identification
• Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions
• Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
• False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image
• CoLES: Contrastive Learning for Event Sequences with Self-Supervision
• Knowledge Graphs and Pre-trained Language Models enhanced Representation Learning for Conversational Recommender Systems
• Conditional Negative Sampling for Contrastive Learning of Visual Representations
• Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation
• SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
• Parametric Instance Classification for Unsupervised Visual Feature Learning
• Video Understanding as Machine Translation
• Deep Active Learning for Computer Vision: Past and Future
• A Contrastive Variational Graph Auto-Encoder for Node Clustering
• Understanding the Behaviour of Contrastive Loss
• Nonlinear Invariant Risk Minimization: A Causal Approach
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and Regression
• Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
• Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
• MMGL: Multi-Scale Multi-View Global-Local Contrastive learning for Semi-supervised Cardiac Image Segmentation
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• An explainable deep vision system for animal classification and detection in trail-camera images with automatic post-deployment retraining
• TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning
• Learning from 2D: Contrastive Pixel-to-Point Knowledge Transfer for 3D Pretraining
• Improving colonoscopy lesion classification using semi-supervised deep learning
• Learn molecular representations from large-scale unlabeled molecules for drug discovery
• Enriched Music Representations with Multiple Cross-modal Contrastive Learning
• Cervical Optical Coherence Tomography Image Classification Based on Contrastive Self-Supervised Texture Learning
• Deep Reinforcement and InfoMax Learning
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Action and Perception as Divergence Minimization
• Mastering Atari with Discrete World Models
• Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
• FaultFormer: Pretraining Transformers for Adaptable Bearing Fault Classification
• Self-supervision for medical image classification: state-of-the-art performance with ~100 labeled training samples per class
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks
• Capturing the physics of MaNGA galaxies with self-supervised Machine Learning
• Learning Representations from Audio-Visual Spatial Alignment
• Self-Supervised Learning with Kernel Dependence Maximization
• Hybrid Discriminative-Generative Training via Contrastive Learning
• Visual Imitation Made Easy
• SemiCurv: Semi-Supervised Curvilinear Structure Segmentation
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• Joint Contrastive Learning for Unsupervised Domain Adaptation
• Boosting Semi-supervised Image Segmentation with Global and Local Mutual Information Regularization
• Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation
• Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model
• Generalizable multi-task, multi-domain deep segmentation of sparse pediatric imaging datasets via multi-scale contrastive regularization and multi-joint anatomical priors
• The DKU-DukeECE Systems for VoxCeleb Speaker Recognition Challenge 2020
• A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learning
• Revisiting Model Stitching to Compare Neural Representations
• Surrogate- and invariance-boosted contrastive learning for data-scarce applications in science
• Towards the Generalization of Contrastive Self-Supervised Learning
• CLDG: Contrastive Learning on Dynamic Graphs
• Relational Self-Supervised Learning on Graphs
• CoReFusion: Contrastive Regularized Fusion for Guided Thermal Super-Resolution
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
• CLIP-ReIdent: Contrastive Training for Player Re-Identification
• A topological solution to object segmentation and tracking
• MAD: Self-Supervised Masked Anomaly Detection Task for Multivariate Time Series
• The Dawn of AI-Native EDA: Opportunities and Challenges of Large Circuit Models
• Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
• Hebbian Semi-Supervised Learning in a Sample Efficiency Setting
• Adaptive Soft Contrastive Learning
• Unsupervised Representation Learning by InvariancePropagation
• GaitFormer: Learning Gait Representations with Noisy Multi-Task Learning
• ChatGPT Code Detection: Techniques for Uncovering the Source of Code
• LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
• Dual Contrastive Learning for Spatio-temporal Representation
• FedDCSR: Federated Cross-domain Sequential Recommendation via Disentangled Representation Learning
• Finding an Unsupervised Image Segmenter in Each of Your Deep Generative Models
• Self-supervised EEG Representation Learning for Automatic Sleep Staging
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition
• Semi-Supervised Visual Representation Learning for Fashion Compatibility
• LoCo: Local Contrastive Representation Learning
• Model-Contrastive Federated Learning
• 3D Human Action Representation Learning via Cross-View Consistency Pursuit
• On the surprising similarities between supervised and self-supervised models
• View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose
• Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
• Contrastive Visual-Linguistic Pretraining
• Deep Contrastive Graph Learning with Clustering-Oriented Guidance
• Quasi-Dense Similarity Learning for Multiple Object Tracking
• Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
• Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
• Learning Salient Boundary Feature for Anchor-free Temporal Action Localization
• Self-Knowledge Distillation based Self-Supervised Learning for Covid-19 Detection from Chest X-Ray Images
• UNav: An Infrastructure-Independent Vision-Based Navigation System for People with Blindness and Low vision
• Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
• A Survey on Self-supervised Pre-training for Sequential Transfer Learning in Neural Networks
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
• Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks
• Contrastive Syn-to-Real Generalization
• Triangle Graph Interest Network for Click-through Rate Prediction
• On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
• Limits on Inferring T-cell Specificity from Partial Information
• Self-supervised Cross-silo Federated Neural Architecture Search
• Debiased Contrastive Learning
• Multi-queue Momentum Contrast for Microvideo-Product Retrieval
• The Next Big Thing(s) in Unsupervised Machine Learning: Five Lessons from Infant Learning
• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• Multimodal Contrastive Training for Visual Representation Learning
• Adaptive Deep Kernel Learning
• Anomalies, Representations, and Self-Supervision
• Contrastive Learning for Compact Single Image Dehazing
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort
• A Self Supervised StyleGAN for Image Annotation and Classification with Extremely Limited Labels
• CCL: Continual Contrastive Learning for LiDAR Place Recognition
• Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
• Motif-Driven Contrastive Learning of Graph Representations
• Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification
• Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation
• Clinically Labeled Contrastive Learning for OCT Biomarker Classification
• On Data-Augmentation and Consistency-Based Semi-Supervised Learning
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• Deep Metric Learning with Spherical Embedding
• Generalization in Reinforcement Learning by Soft Data Augmentation
• Artificial and beneficial -- Exploiting artificial images for aerial vehicle detection
• Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
• Improving Weakly Supervised Temporal Action Localization by Exploiting Multi-resolution Information in Temporal Domain
• GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation
• An Asymmetric Contrastive Loss for Handling Imbalanced Datasets
• Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
• How to Train Your Energy-Based Model for Regression
• Robust Multiview Multimodal Driver Monitoring System Using Masked Multi-Head Self-Attention
• Universum-inspired Supervised Contrastive Learning
• Pre-Trained Models: Past, Present and Future
• Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering
• On Episodes, Prototypical Networks, and Few-shot Learning
• The IDLAB VoxCeleb Speaker Recognition Challenge 2020 System Description
• TriBYOL: Triplet BYOL for Self-Supervised Representation Learning
• Few-shot Image Generation via Cross-domain Correspondence
• Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classification
• Deep residential representations: Using unsupervised learning to unlock elevation data for geo-demographic prediction
• Contrastive Learning of Person-independent Representations for Facial Action Unit Detection
• PhysiQ: Off-site Quality Assessment of Exercise in Physical Therapy
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Large-Scale Hyperspectral Image Clustering Using Contrastive Learning
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• NewsEmbed: Modeling News through Pre-trained Document Representations
• CLAR: Contrastive Learning of Auditory Representations
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation
• Autoencoding Variational Autoencoder
• Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild
• Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization
• Auxiliary Task Reweighting for Minimum-data Learning
• Contrastive Predictive Coding for Anomaly Detection
• Elastic-InfoGAN: Unsupervised Disentangled Representation Learning in Class-Imbalanced Data
• Imposing Relation Structure in Language-Model Embeddings Using Contrastive Learning
• Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Clouds
• Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy
• Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation Learning
• Joint Learning Content and Degradation Aware Feature for Blind Super-Resolution
• CAPT: Contrastive Pre-Training for Learning Denoised Sequence Representations
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties
• Class Gradient Projection For Continual Learning
• Self-Damaging Contrastive Learning
• Enabling Large Batch Size Training for DNN Models Beyond the Memory Limit While Maintaining Performance
• RPT: Toward Transferable Model on Heterogeneous Researcher Data via Pre-Training
• A compact neuromorphic system for ultra-energy-efficient, on-device robot localization
• SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
• How Will It Drape Like? Capturing Fabric Mechanics from Depth Images
• Low-resource finetuning of foundation models beats state-of-the-art in histopathology
• Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
• Hierarchically Organized Latent Modules for Exploratory Search in Morphogenetic Systems
• Bi-tuning of Pre-trained Representations
• Multi-organ segmentation: a progressive exploration of learning paradigms under scarce annotation
• Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
• Unsupervised Traffic Scene Generation with Synthetic 3D Scene Graphs
• Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data
• Fearless Luminance Adaptation: A Macro-Micro-Hierarchical Transformer for Exposure Correction
• D2RL: Deep Dense Architectures in Reinforcement Learning
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
• Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives
• Self-supervised Temporal Discriminative Learning for Video Representation Learning
• Progressive Domain Expansion Network for Single Domain Generalization
• Test time Adaptation through Perturbation Robustness
• Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
• Deep Partition Aggregation: Provable Defense against General Poisoning Attacks
• AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
• HarperValleyBank: A Domain-Specific Spoken Dialog Corpus
• Online Adversarial Purification based on Self-Supervision
• Mpox-AISM: AI-Mediated Super Monitoring for Mpox and Like-Mpox
• Contrastive Registration for Unsupervised Medical Image Segmentation
• Continual Contrastive Learning for Image Classification
• Convolutional Channel-wise Competitive Learning for the Forward-Forward Algorithm
• Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains
• A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance
• RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification
• Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning
• Self-supervised Modal and View Invariant Feature Learning
• Learning Generalizable Visual Representations via Interactive Gameplay
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
• Deep Double Self-Expressive Subspace Clustering
• Transfer Learning Application of Self-supervised Learning in ARPES
• Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights
• SE(3)-Equivariant and Noise-Invariant 3D Rigid Motion Tracking in Brain MRI
• Self-supervised Learning from a Multi-view Perspective
• Doubly Contrastive Deep Clustering
• Joint Contrastive Learning with Infinite Possibilities
• A Co-training Approach for Noisy Time Series Learning
• Momentum^2 Teacher: Momentum Teacher with Momentum Statistics for Self-Supervised Learning
• Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation
• Exploring Instance Relations for Unsupervised Feature Embedding
• Implicit Rank-Minimizing Autoencoder
• Distilling Localization for Self-Supervised Representation Learning
• Self-supervised Neural Architecture Search
• Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems
• Proxy-based Item Representation for Attribute and Context-aware Recommendation
• Efficient Self-Supervision using Patch-based Contrastive Learning for Histopathology Image Segmentation
• Vector Quantized Contrastive Predictive Coding for Template-based Music Generation
• Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
• Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
• Federated Self-Supervised Learning in Heterogeneous Settings: Limits of a Baseline Approach on HAR
• Multi-Dataset Benchmarks for Masked Identification using Contrastive Representation Learning
• Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning
• Multimodal Semi-Supervised Learning for 3D Objects
• A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
• XIRL: Cross-embodiment Inverse Reinforcement Learning
• Contrastive Learning Improves Model Robustness Under Label Noise
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model
• Deep Clustering by Semantic Contrastive Learning
• MiCE: Mixture of Contrastive Experts for Unsupervised Image Clustering
• Fairness-Aware Node Representation Learning
• Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
• Self-Guided Contrastive Learning for BERT Sentence Representations
• Run Away From your Teacher: Understanding BYOL by a Novel Self-Supervised Approach
• Spatially Consistent Representation Learning
• The Spatially-Correlative Loss for Various Image Translation Tasks
• Generalizable Pancreas Segmentation via a Dual Self-Supervised Learning Framework
• Understand and Improve Contrastive Learning Methods for Visual Representation: A Review
• CO2: Consistent Contrast for Unsupervised Visual Representation Learning
• Modeling Disease Progression in Mild Cognitive Impairment and Alzheimer's Disease with Digital Twins
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation
• Confidence-Calibrated Face and Kinship Verification
• LibAUC: A Deep Learning Library for X-Risk Optimization
• Cross-domain few-shot learning with unlabelled data
• Exploring the Use of Contrastive Language-Image Pre-Training for Human Posture Classification: Insights from Yoga Pose Analysis
• Evaluating representations by the complexity of learning low-loss predictors
• A vector quantized masked autoencoder for audiovisual speech emotion recognition
• Sentence Embeddings using Supervised Contrastive Learning
• Non-contrastive representation learning for intervals from well logs
• InferCode: Self-Supervised Learning of Code Representations by Predicting Subtrees
• Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
• Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learning
• Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
• Learning Robust Representation through Graph Adversarial Contrastive Learning
• Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
• COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations
• Parallel Training of Deep Networks with Local Updates
• PointSmile: Point Self-supervised Learning via Curriculum Mutual Information
• Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
• Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction
• Improving Transformation Invariance in Contrastive Representation Learning
• Multi-label Contrastive Predictive Coding
• Supporting Clustering with Contrastive Learning
• RPT: Relational Pre-trained Transformer Is Almost All You Need towards Democratizing Data Preparation
• Spatial Dependency Networks: Neural Layers for Improved Generative Image Modeling
• 3KG: Contrastive Learning of 12-Lead Electrocardiograms using Physiologically-Inspired Augmentations
• Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning
• Evolution Is All You Need: Phylogenetic Augmentation for Contrastive Learning
• Cluster-Guided Unsupervised Domain Adaptation for Deep Speaker Embedding
• Camera-aware Proxies for Unsupervised Person Re-Identification
• All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization
• Deciphering and integrating invariants for neural operator learning with various physical mechanisms
• Learning from Label Relationships in Human Affect
• Facial Tic Detection in Untrimmed Videos of Tourette Syndrome Patients
• Intervention Design for Effective Sim2Real Transfer
• Contrastive Representation Learning for Whole Brain Cytoarchitectonic Mapping in Histological Human Brain Sections
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models
• Improving the Transferability of Adversarial Attacks on Face Recognition with Beneficial Perturbation Feature Augmentation
• Temporal Context Aggregation for Video Retrieval with Contrastive Learning
• Data Augmentation for Object Detection via Differentiable Neural Rendering
• A Novel Semisupervised Contrastive Regression Framework for Forest Inventory Mapping with Multisensor Satellite Data
• Mini-batch graphs for robust image classification
• YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID
• Instance Localization for Self-supervised Detection Pretraining
• Contrastive Semi-Supervised Learning for 2D Medical Image Segmentation
• Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
• No True State-of-the-Art? OOD Detection Methods are Inconsistent across Datasets
• Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
• Self-supervised Video Object Segmentation
• Semi-visible jets, energy-based models, and self-supervision
• ContrastNER: Contrastive-based Prompt Tuning for Few-shot NER
• Adversarial Training with Contrastive Learning in NLP
• OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Data
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
• Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
• Refining Pseudo Labels with Clustering Consensus over Generations for Unsupervised Object Re-identification
• For self-supervised learning, Rationality implies generalization, provably
• Unsupervised Hashing with Contrastive Information Bottleneck
• An Empirical Investigation of Representation Learning for Imitation
• Self-Supervision, Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations
• Contrastive Learning for Context-aware Neural Machine TranslationUsing Coreference Information
• Semi-Supervised Few-Shot Intent Classification and Slot Filling
• A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection
• Does a Face Mask Protect my Privacy?: Deep Learning to Predict Protected Attributes from Masked Face Images
• Local Contrastive Feature learning for Tabular Data
• Object classification on video data of meteors and meteor-like phenomena: algorithm and data
• Combining Self-Supervised and Supervised Learning with Noisy Labels
• HateProof: Are Hateful Meme Detection Systems really Robust?
• Self-Supervised Out-of-Distribution Detection in Brain CT Scans
• Transformers for One-Shot Visual Imitation
• Attention over learned object embeddings enables complex visual reasoning
• MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
• Unsupervised Pre-Training for 3D Leaf Instance Segmentation
• Towards Attention-based Contrastive Learning for Audio Spoof Detection
• Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation
• CUPID: Adaptive Curation of Pre-training Data for Video-and-Language Representation Learning
• Large-Scale Self- and Semi-Supervised Learning for Speech Translation
• Online Deep Clustering for Unsupervised Representation Learning
• Language-Driven Image Style Transfer
• Contrastive Learning for Robust Android Malware Familial Classification
• Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
• No MCMC for me: Amortized sampling for fast and stable training of energy-based models
• VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
• Dialogue Response Ranking Training with Large-Scale Human Feedback Data
• Elsa: Energy-based learning for semi-supervised anomaly detection
• Generative Models as a Data Source for Multiview Representation Learning
• Augmentation Pathways Network for Visual Recognition
• Real-Time Idling Vehicles Detection using Combined Audio-Visual Deep Learning
• CoDeGAN: Contrastive Disentanglement for Generative Adversarial Network
• A Scalable and Transferable Time Series Prediction Framework for Demand Forecasting
• Complex QA and language models hybrid architectures, Survey
• Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision
• Auxiliary Tasks Speed Up Learning PointGoal Navigation
• A Multi-Stage Attentive Transfer Learning Framework for Improving COVID-19 Diagnosis
• Reviewing Evolution of Learning Functions and Semantic Information Measures for Understanding Deep Learning
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Meta Approach to Data Augmentation Optimization
• Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels
• Few-shot Open-set Recognition by Transformation Consistency
• Transferred Discrepancy: Quantifying the Difference Between Representations
• Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
• CoKe: Localized Contrastive Learning for Robust Keypoint Detection
• Contrastive Reasoning in Neural Networks
• Estimating Galactic Distances From Images Using Self-supervised Representation Learning
• SIRL: Similarity-based Implicit Representation Learning
• Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
• DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer
• INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields
• Self-supervised Document Clustering Based on BERT with Data Augment
• A Survey of Spatio-Temporal EEG data Analysis: from Models to Applications
• Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
• Mitigating Spurious Correlations for Self-supervised Recommendation
• Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
• Self-labeled Conditional GANs
• Representation Learning via Consistent Assignment of Views to Clusters
• Calibrating and Improving Graph Contrastive Learning
• Semi-Supervising Learning, Transfer Learning, and Knowledge Distillation with SimCLR
• Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation
• Neural Methods for Point-wise Dependency Estimation
• Learning Cross-Scale Visual Representations for Real-Time Image Geo-Localization
• Multi-Object Tracking with Deep Learning Ensemble for Unmanned Aerial System Applications
• Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Machine learning with limited data
• DistillCSE: Distilled Contrastive Learning for Sentence Embeddings
• Contrastive Distillation on Intermediate Representations for Language Model Compression
• Slot Contrastive Networks: A Contrastive Approach for Representing Objects
• LRC-BERT: Latent-representation Contrastive Knowledge Distillation for Natural Language Understanding
• Pneumonia Detection on Chest X-ray using Radiomic Features and Contrastive Learning
• Unsupervised Pre-training for Person Re-identification
• Deep Lesion Tracker: Monitoring Lesions in 4D Longitudinal Imaging Studies
• GENNAPE: Towards Generalized Neural Architecture Performance Estimators
• Self-supervised Video Representation Learning by Context and Motion Decoupling
• Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup
• DEMI: Discriminative Estimator of Mutual Information
• Advances in Preference-based Reinforcement Learning: A Review
• Self-Supervised Ranking for Representation Learning
• Learning Object-Centric Video Models by Contrasting Sets
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
• Multilingual BERT Post-Pretraining Alignment
• Representation learning for improved interpretability and classification accuracy of clinical factors from EEG
• Longitudinal Self-supervised Learning Using Neural Ordinary Differential Equation
• Self-supervised Graph Representation Learning via Bootstrapping
• CUCL: Codebook for Unsupervised Continual Learning
• CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation
• PAC-Bayesian Contrastive Unsupervised Representation Learning
• CLCC: Contrastive Learning for Color Constancy
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
• From Multimodal to Unimodal Attention in Transformers using Knowledge Distillation
• Contrastive Multi-View Textual-Visual Encoding: Towards One Hundred Thousand-Scale One-Shot Logo Identification
• Action-Based Representation Learning for Autonomous Driving
• Bootstrap Equilibrium and Probabilistic Speaker Representation Learning for Self-supervised Speaker Verification
• Conditional independence for pretext task selection in Self-supervised speech representation learning
• Unsupervised deep learning for grading of age-related macular degeneration using retinal fundus images
• Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
• Self-supervised pre-training and contrastive representation learning for multiple-choice video QA
• A Feature Fusion-Net Using Deep Spatial Context Encoder and Nonstationary Joint Statistical Model for High Resolution SAR Image Classification
• Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
• Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
• A Cross-Level Information Transmission Network for Predicting Phenotype from New Genotype: Application to Cancer Precision Medicine
• SimTriplet: Simple Triplet Representation Learning with a Single GPU
• Leveraging Human Feedback to Evolve and Discover Novel Emergent Behaviors in Robot Swarms
• Environment Predictive Coding for Embodied Agents
• EqCo: Equivalent Rules for Self-supervised Contrastive Learning
• Self-supervised Representation Learning with Relative Predictive Coding
• An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
• TypoSwype: An Imaging Approach to Detect Typo-Squatting
• Towards Cardiac MRI Foundation Models: Comprehensive Visual-Tabular Representations for Whole-Heart Assessment and Beyond
• Self-Supervised Learning of a Biologically-Inspired Visual Texture Model
• Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
• SleepPriorCL: Contrastive Representation Learning with Prior Knowledge-based Positive Mining and Adaptive Temperature for Sleep Staging
• A Machine Learning Enhanced Approach for Automated Sunquake Detection in Acoustic Emission Maps
• Function Contrastive Learning of Transferable Meta-Representations
• Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR Data
• Center-wise Local Image Mixture For Contrastive Representation Learning
• A Simple Framework for Uncertainty in Contrastive Learning
• Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
• RankingMatch: Delving into Semi-Supervised Learning with Consistency Regularization and Ranking Loss
• Label Contrastive Coding based Graph Neural Network for Graph Classification
• ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
• Contrastive Learning for Multi-Modal Automatic Code Review
• Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers
• Learning About Objects by Learning to Interact with Them
• Self-supervised Visual Attribute Learning for Fashion Compatibility
• Self-Supervised Representations Improve End-to-End Speech Translation
• Motion-Focused Contrastive Learning of Video Representations
• Multi-Task Self-Supervised Pre-Training for Music Classification
• Training Neural Networks with Fixed Sparse Masks
• Simple Distillation Baselines for Improving Small Self-supervised Models
• Evolutionary Augmentation Policy Optimization for Self-supervised Learning
• Anomaly Detection on X-Rays Using Self-Supervised Aggregation Learning
• Imbalance-Aware Self-Supervised Learning for 3D Radiomic Representations
• AutoLTS: Automating Cycling Stress Assessment via Contrastive Learning and Spatial Post-processing
• Self-supervised Tumor Segmentation through Layer Decomposition
• Built Year Prediction from Buddha Face with Heterogeneous Labels
• MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
• Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis
• Learning Image Representations for Content Based Image Retrieval of Radiotherapy Treatment Plans
• Unsupervised Visual Attention and Invariance for Reinforcement Learning
• Contrastive Self-Supervised Learning for Spatio-Temporal Analysis of Lung Ultrasound Videos
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning
• LMT: Longitudinal Mixing Training, a Framework to Predict Disease Progression from a Single Image
• Towards Corruption-Agnostic Robust Domain Adaptation
• CoReS: Compatible Representations via Stationarity
• DeepfakeUCL: Deepfake Detection via Unsupervised Contrastive Learning
• Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection
• TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
• Bootstrapping Contrastive Learning Enhanced Music Cold-Start Matching
• COBRA: Contrastive Bi-Modal Representation Algorithm
• A General-Purpose Transferable Predictor for Neural Architecture Search
• Unified Multi-modal Diagnostic Framework with Reconstruction Pre-training and Heterogeneity-combat Tuning
• S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
• Contrastive Neural Processes for Self-Supervised Learning
• Self-supervised Contrastive Learning for Irrigation Detection in Satellite Imagery
• Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
• Do Explicit Alignments Robustly Improve Multilingual Encoders?
• Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning
• Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning
• Contrastive Unsupervised Learning for Audio Fingerprinting
• Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
• Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
• Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
• Learning to Track Instances without Video Annotations
• Jigsaw Clustering for Unsupervised Visual Representation Learning
• Unsupervised Document Embedding via Contrastive Augmentation
• Rethinking movie genre classification with fine-grained semantic clustering
• Unobtrusive Pain Monitoring in Older Adults with Dementia using Pairwise and Contrastive Training
• Latent Feature Representation via Unsupervised Learning for Pattern Discovery in Massive Electron Microscopy Image Volumes
• Deep learning for fast MR imaging: a review for learning reconstruction from incomplete k-space data
• Are Fewer Labels Possible for Few-shot Learning?
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models
• Self-supervised Visual Reinforcement Learning with Object-centric Representations
• Dual Contradistinctive Generative Autoencoder
• Online Exemplar Fine-Tuning for Image-to-Image Translation
• StackMix: A complementary Mix algorithm
• Contrastive Unpaired Translation using Focal Loss for Patch Classification
• EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning
• Triplet Contrastive Learning for Brain Tumor Classification
• Interventional Video Grounding with Dual Contrastive Learning
• Multi-Level Graph Contrastive Learning
• TENET: A Time-reversal Enhancement Network for Noise-robust ASR
• The Animal ID Problem: Continual Curation
• Enabling On-Device Self-Supervised Contrastive Learning With Selective Data Contrast
• Loss Function Entropy Regularization for Diverse Decision Boundaries
• SUVR: A Search-based Approach to Unsupervised Visual Representation Learning
• OFAR: A Multimodal Evidence Retrieval Framework for Illegal Live-streaming Identification
• Multiview Representation Learning from Crowdsourced Triplet Comparisons
• Energy-Based Models with Applications to Speech and Language Processing
• FedSC: Federated Learning with Semantic-Aware Collaboration
• Using Backbone Foundation Model for Evaluating Fairness in Chest Radiography Without Demographic Data
• Damage GAN: A Generative Model for Imbalanced Data
• DSS: Synthesizing long Digital Ink using Data augmentation, Style encoding and Split generation
• DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
• Experimenting with Additive Margins for Contrastive Self-Supervised Speaker Verification
• A Mathematical Framework for Learning Probability Distributions
• Co-supervised learning paradigm with conditional generative adversarial networks for sample-efficient classification
• Neural Network Training on In-memory-computing Hardware with Radix-4 Gradients
• Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
• Learnable Adaptive Cosine Estimator (LACE) for Image Classification
• Towards Demystifying Representation Learning with Non-contrastive Self-supervision
• Self-supervised Pseudo Multi-class Pre-training for Unsupervised Anomaly Detection and Segmentation in Medical Images
• Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Geographical Knowledge-driven Representation Learning for Remote Sensing Images
• Clustering-Based Representation Learning through Output Translation and Its Application to Remote--Sensing Images
• Contrastive Attraction and Contrastive Repulsion for Representation Learning
• Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling
• Polyphone Disambiguation in Mandarin Chinese with Semi-Supervised Learning
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
• Learning Visual Representations for Transfer Learning by Suppressing Texture
• An iterative framework for self-supervised deep speaker representation learning
• BalaGAN: Image Translation Between Imbalanced Domains via Cross-Modal Transfer
• Deep Manifold Transformation for Nonlinear Dimensionality Reduction
• Neural, Symbolic and Neural-Symbolic Reasoning on Knowledge Graphs
• From Language Games to Drawing Games
• Learning Retrospective Knowledge with Reverse Reinforcement Learning
• Embodied Self-supervised Learning by Coordinated Sampling and Training
• Classify and Generate: Using Classification Latent Space Representations for Image Generations
• Multilayer Clustered Graph Learning
• GeomCA: Geometric Evaluation of Data Representations
• Double cycle-consistent generative adversarial network for unsupervised conditional generation
• Contrastive Embeddings for Neural Architectures
• Self-supervised Visual-LiDAR Odometry with Flip Consistency
• Pre-training of Deep RL Agents for Improved Learning under Domain Randomization
• Unsupervised Discriminative Learning of Sounds for Audio Event Classification
• CLOUD: Contrastive Learning of Unsupervised Dynamics
• Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
• Supervised Graph Contrastive Pretraining for Text Classification
• Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning
• CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising
• Contrastive Learning of Global-Local Video Representations
• Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network
• Bayesian Robust Optimization for Imitation Learning
• Neural Architecture Search with Random Labels
• Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning
• USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning
• Data Cleansing with Contrastive Learning for Vocal Note Event Annotations
• A Style and Semantic Memory Mechanism for Domain Generalization
• Addressing Feature Suppression in Unsupervised Visual Representations
• Long-range and hierarchical language predictions in brains and algorithms
• A Unified Mixture-View Framework for Unsupervised Representation Learning
• Ranking Neural Checkpoints
• Self-supervised Feature Learning via Exploiting Multi-modal Data for Retinal Disease Diagnosis
• CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion
• One-bit Supervision for Image Classification: Problem, Solution, and Beyond
• Exploring Representation Learning for Small-Footprint Keyword Spotting
• An Attention Mechanism with Multiple Knowledge Sources for COVID-19 Detection from CT Images
• Shuffle & Divide: Contrastive Learning for Long Text
• Multi-source Few-shot Domain Adaptation
• Survey: Transformer based Video-Language Pre-training
• CEIL: A General Classification-Enhanced Iterative Learning Framework for Text Clustering
• Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
• Masked Contrastive Learning for Anomaly Detection
• Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning
• Don't miss the Mismatch: Investigating the Objective Function Mismatch for Unsupervised Representation Learning
• Transfer Learning with Pre-trained Conditional Generative Models
• Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
• Neural Audio Fingerprint for High-specific Audio Retrieval based on Contrastive Learning
• Net2Brain: A Toolbox to compare artificial vision models with human brain responses
• Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
• Cross-domain Transfer of defect features in technical domains based on partial target data
• A Brief Summary of Interactions Between Meta-Learning and Self-Supervised Learning
• Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning
• Watching Too Much Television is Good: Self-Supervised Audio-Visual Representation Learning from Movies and TV Shows
• Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
• Land Cover Mapping in Limited Labels Scenario: A Survey
• Distant Domain Transfer Learning for Medical Imaging
• Aggregative Self-Supervised Feature Learning from a Limited Sample
• Shot in the Dark: Few-Shot Learning with No Base-Class Labels
• Robust Representation Learning via Perceptual Similarity Metrics
• Unsupervised Image Classification for Deep Representation Learning
• Shifting Transformation Learning for Out-of-Distribution Detection
• Human Inspired Progressive Alignment and Comparative Learning for Grounded Word Acquisition
• Leveraging Self-Supervised Vision Transformers for Segmentation-based Transfer Function Design
• Group-wise Contrastive Learning for Neural Dialogue Generation
• Knowledge Distillation Meets Self-Supervision
• T-Rep: Representation Learning for Time Series using Time-Embeddings
• Unsupervised Anomaly Detection From Semantic Similarity Scores
• Unsupervised learning on spontaneous retinal activity leads to efficient neural representation geometry
• VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification
• Domain Contrast for Domain Adaptive Object Detection
• Semi-Supervised Pipe Video Temporal Defect Interval Localization
• MACK: Mismodeling Addressed with Contrastive Knowledge
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
• Self-supervised Text-independent Speaker Verification using Prototypical Momentum Contrastive Learning
• Unsupervised Visual Representation Learning by Tracking Patches in Video
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
• Learning Interclass Relations for Image Classification
• WildGait: Learning Gait Representations from Raw Surveillance Streams
• About Explicit Variance Minimization: Training Neural Networks for Medical Imaging With Limited Data Annotations
• Malfustection: Obfuscated Malware Detection and Malware Classification with Data Shortage by Combining Semi-Supervised and Contrastive Learning
• Semi-Supervised Vision Transformers
• Learning Representations for Pixel-based Control: What Matters and Why?
• Learning to Align Sequential Actions in the Wild
• PyTorchVideo: A Deep Learning Library for Video Understanding
• Boosting Supervised Learning Performance with Co-training
• Object-Aware Cropping for Self-Supervised Learning
• Applying SoftTriple Loss for Supervised Language Model Fine Tuning
• Spherical Sliced-Wasserstein
• DeCoR: Defy Knowledge Forgetting by Predicting Earlier Audio Codes
• CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
• Identical and Fraternal Twins: Fine-Grained Semantic Contrastive Learning of Sentence Representations
• Learning Purified Feature Representations from Task-irrelevant Labels
• WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
• Improving Lesion Segmentation in Medical Images by Global and Regional Feature Compensation
• Intrinsic and Extrinsic Factor Disentanglement for Recommendation in Various Context Scenarios
• Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
• Uncover and Unlearn Nuisances: Agnostic Fully Test-Time Adaptation
• Hierarchical Text Classification Using Contrastive Learning Informed Path Guided Hierarchy
• A Transformer-based Autoregressive Decoder Architecture for Hierarchical Text Classification
• Neuro-Symbolic Contrastive Learning for Cross-domain Inference
• Supervised Momentum Contrastive Learning for Few-Shot Classification
• Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
• Scale-specific auxiliary multi-task contrastive learning for deep liver vessel segmentation
• Domain-Aware Augmentations for Unsupervised Online General Continual Learning
• Transformer-based Self-supervised Multimodal Representation Learning for Wearable Emotion Recognition
• Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
• ContraCluster: Learning to Classify without Labels by Contrastive Self-Supervision and Prototype-Based Semi-Supervision
• On the robustness of self-supervised representations for multi-view object classification
• Improving Image Clustering through Sample Ranking and Its Application to remote--sensing images
• CLOP: Video-and-Language Pre-Training with Knowledge Regularizations
• Dissecting Image Crops
• SIR: Self-supervised Image Rectification via Seeing the Same Scene from Multiple Different Lenses
• Improving Object Detection with Selective Self-supervised Self-training
• CLAWS: Contrastive Learning with hard Attention and Weak Supervision
• Momentum Contrast Speaker Representation Learning
• IDEAL: Independent Domain Embedding Augmentation Learning
• What data do we need for training an AV motion planner?
• Contrastive Rendering for Ultrasound Image Segmentation
• Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
• A Self-supervised Approach for Semantic Indexing in the Context of COVID-19 Pandemic
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms
• Personalizing Pre-trained Models
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
• Progressive Stage-wise Learning for Unsupervised Feature Representation Enhancement
• D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
• Low-Power Multi-Camera Object Re-Identification using Hierarchical Neural Networks
• A Framework for Generative and Contrastive Learning of Audio Representations
• Generative Modeling for Multi-task Visual Learning
• What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
• Representation Learning for Sequence Data with Deep Autoencoding Predictive Components
• eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges
• Similarity Analysis of Self-Supervised Speech Representations
• LabelEnc: A New Intermediate Supervision Method for Object Detection
• TreeGAN: Incorporating Class Hierarchy into Image Generation
• Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
• Contrastive Mixup: Self- and Semi-Supervised learning for Tabular Domain
• Resource and data efficient self supervised learning
• Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
• X-model: Improving Data Efficiency in Deep Learning with A Minimax Model
• Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuning
• K-Shot Contrastive Learning of Visual Features with Multiple Instance Augmentations
• Explicitly Modeling the Discriminability for Instance-Aware Visual Object Tracking
• Interpretable contrastive word mover's embedding
• Free-Form Image Inpainting via Contrastive Attention Network
• Unsupervised Object Detection with LiDAR Clues
• Data Augmentation via Structured Adversarial Perturbations
• Feature Distillation With Guided Adversarial Contrastive Learning
• Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
• On the Marginal Benefit of Active Learning: Does Self-Supervision Eat Its Cake?
• Few Shot Learning With No Labels
• The emergence of visual semantics through communication games
• Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
• SISE-PC: Semi-supervised Image Subsampling for Explainable Pathology
• Self-supervised Text-to-SQL Learning with Header Alignment Training
• Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning
• UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
• Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning
• Self-supervised Regularization for Text Classification
• Complementary Relation Contrastive Distillation
• Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning
• Self-Supervised Dynamic Networks for Covariate Shift Robustness
• DTG-Net: Differentiated Teachers Guided Self-Supervised Video Action Recognition
• Disentangle Perceptual Learning through Online Contrastive Learning
• Contrastive Mixture of Posteriors for Counterfactual Inference, Data Integration and Fairness
• Low Budget Active Learning via Wasserstein Distance: An Integer Programming Approach
• Revisiting Catastrophic Forgetting in Class Incremental Learning
• Dynamic Convolution for 3D Point Cloud Instance Segmentation
• Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
• Self-supervised Learning for Semi-supervised Temporal Language Grounding
• Information Theory-Guided Heuristic Progressive Multi-View Coding
• SERE: Exploring Feature Self-relation for Self-supervised Transformer
• Similarity Guided Deep Face Image Retrieval
• Feature Lenses: Plug-and-play Neural Modules for Transformation-Invariant Visual Representations
• Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving
• Improve Unsupervised Pretraining for Few-label Transfer
• Using contrastive learning to improve the performance of steganalysis schemes
• What Remains of Visual Semantic Embeddings
• Experimenting with Self-Supervision using Rotation Prediction for Image Captioning
• Attribute Guided Sparse Tensor-Based Model for Person Re-Identification
• Boosting Few-Shot Classification with View-Learnable Contrastive Learning
• Segmentation of VHR EO Images using Unsupervised Learning
• Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
• Contrastive learning of strong-mixing continuous-time stochastic processes
• Unsupervised Disentanglement without Autoencoding: Pitfalls and Future Directions
• Topo2vec: Topography Embedding Using the Fractal Effect
• Self-supervised similarity search for large scientific datasets
• Cross-modal Image Retrieval with Deep Mutual Information Maximization
• MIC: Model-agnostic Integrated Cross-channel Recommenders
• Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE
• Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models
• Pairwise Supervised Contrastive Learning of Sentence Representations
• Improved Detection of Face Presentation Attacks Using Image Decomposition
• Stochastic Contrastive Learning
• Semi-Supervised Text Classification via Self-Pretraining
• Overcoming the Domain Gap in Contrastive Learning of Neural Action Representations
• Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation
• Multi-axis Attentive Prediction for Sparse EventData: An Application to Crime Prediction
• Self-Supervised Motion Retargeting with Safety Guarantee
• I know why you like this movie: Interpretable Efficient Multimodal Recommender
• Explaining Representation by Mutual Information
• Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
• Color Variants Identification in Fashion e-commerce via Contrastive Self-Supervised Representation Learning
• Life is not black and white -- Combining Semi-Supervised Learning with fuzzy labels
• Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
• Active Learning at the ImageNet Scale
• Self-Supervised Learning of Context-Aware Pitch Prosody Representations
• Contrastive Learning of Visual-Semantic Embeddings
• Natural Attribute-based Shift Detection
• Graph Partner Neural Networks for Semi-Supervised Learning on Graphs
• Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning
• Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles
• C-SL: Contrastive Sound Localization with Inertial-Acoustic Sensors
• Self-Supervised Visual Representation Learning Using Lightweight Architectures
• Understanding the World Through Action
• Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task
• Inverse Problems Leveraging Pre-trained Contrastive Representations
• MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling
• Meta-Learning to Improve Pre-Training
• Is High Variance Unavoidable in RL? A Case Study in Continuous Control
• Class Interference Regularization
• Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
• Network representation learning: A macro and micro view
• Label-Efficient Multi-Task Segmentation using Contrastive Learning
• A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification
• ScaleNet: An Unsupervised Representation Learning Method for Limited Information
• RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation
• ShapeY: Measuring Shape Recognition Capacity Using Nearest Neighbor Matching
• Towards All-around Knowledge Transferring: Learning From Task-irrelevant Labels
• Training Efficiency and Robustness in Deep Learning
• Unsupervised Representation Learning via Neural Activation Coding
• Bootstrapping User and Item Representations for One-Class Collaborative Filtering
• Exploiting Liver CT scans in Colorectal Carcinoma genomics mutation classification
• Label-free Monitoring of Self-Supervised Learning Progress
• Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
• Transferrable Contrastive Learning for Visual Domain Adaptation
• Unified Framework for Feature Extraction based on Contrastive Learning
• An empirical study of domain-agnostic semi-supervised learning via energy-based models: joint-training and pre-training
• Joint Learning of Neural Transfer and Architecture Adaptation for Image Recognition
• Domain-Agnostic Clustering with Self-Distillation
• Contrastive Masked Autoencoders for Character-Level Open-Set Writer Identification
• NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models
• Boosting Video Representation Learning with Multi-Faceted Integration
• Unsupervised Speech Representation Learning for Behavior Modeling using Triplet Enhanced Contextualized Networks
• Unsupervised Discovery of the Long-Tail in Instance Segmentation Using Hierarchical Self-Supervision
• AAG: Self-Supervised Representation Learning by Auxiliary Augmentation with GNT-Xent Loss
• Synthesizing Photorealistic Images with Deep Generative Learning
• Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation
• Balancing Robustness and Sensitivity using Feature Contrastive Learning
• Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
• PCPs: Patient Cardiac Prototypes
• Coarse-to-Fine Memory Matching for Joint Retrieval and Classification
• Self-Tuning for Data-Efficient Deep Learning
• Size Matters: Foundation Model for Czech HTML documents
• Three Pillars improving Vision Foundation Model Distillation for Lidar
• CLEVE: Contrastive Pre-training for Event Extraction
• 2nd Place Solution to Facebook AI Image Similarity Challenge Matching Track
• Hybrid BYOL-ViT: Efficient approach to deal with small datasets
• Neural Random Projection: From the Initial Task To the Input Similarity Problem
• Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing
• Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks
• About contrastive unsupervised representation learning for classification and its convergence
• FROST: Faster and more Robust One-shot Semi-supervised Training
• A Meta Learning Approach to Discerning Causal Graph Structure
• Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training
• Generating Relevant and Coherent Dialogue Responses using Self-separated Conditional Variational AutoEncoders
• Deep Unsupervised Image Anomaly Detection: An Information Theoretic Framework
• Computer-aided Tumor Diagnosis in Automated Breast Ultrasound using 3D Detection Network
• QK Iteration: A Self-Supervised Representation Learning Algorithm for Image Similarity
• Learning Representations on the Unit Sphere: Investigating Angular Gaussian and von Mises-Fisher Distributions for Online Continual Learning
• Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
• Distilling Visual Priors from Self-Supervised Learning
• R${}^2$-Net: Relation of Relation Learning Network for Sentence Semantic Matching
• Atlas Based Representation and Metric Learning on Manifolds
• Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data
• Langevin Cooling for Domain Translation
• GenURL: A General Framework for Unsupervised Representation Learning
• Contrastive String Representation Learning using Synthetic Data
• CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction
• Contrastive Active Inference
• Deep Learning-based Frozen Section to FFPE Translation
• Proceedings of the First Workshop on Weakly Supervised Learning (WeaSuL)
• Explicit homography estimation improves contrastive self-supervised learning
• The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks
• Contrast R-CNN for Continual Learning in Object Detection
• Cost-Efficient Online Hyperparameter Optimization