Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Abstract

Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large number of explicit pairwise feature comparisons, which is computationally challenging. In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, our method simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, we use a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view. Our method can be trained with large and small batches and can scale to unlimited amounts of data. Compared to previous contrastive methods, our method is more memory efficient since it does not require a large memory bank or a special momentum network. In addition, we also propose a new data augmentation strategy, multi-crop, that uses a mix of views with different resolutions in place of two full-resolution views, without increasing the memory or compute requirements much. We validate our findings by achieving 75.3% top-1 accuracy on ImageNet with ResNet-50, as well as surpassing supervised pretraining on all the considered transfer tasks.

NeurIPS 2020

References in corpus (21)

• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
• FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
• Improved Baselines with Momentum Contrastive Learning
• Learning deep representations by mutual information estimation and maximization
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Unsupervised Data Augmentation for Consistency Training
• Momentum Contrast for Unsupervised Visual Representation Learning
• Mixed Precision Training
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Contrastive Multiview Coding
• Large Batch Training of Convolutional Networks
• Prototypical Contrastive Learning of Unsupervised Representations
• Large Scale Adversarial Representation Learning
• Unsupervised Learning by Predicting Noise
• Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey
• Supervised Contrastive Learning
• Unsupervised Deep Learning by Neighbourhood Discovery
• Pruning Convolutional Neural Networks with Self-Supervision
• Are Labels Necessary for Neural Architecture Search?

Cited by in corpus (318)

• Diffusion Models in Vision: A Survey
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision
• DINOv2: Learning Robust Visual Features without Supervision
• BEiT: BERT Pre-Training of Image Transformers
• Contrastive Representation Learning: A Framework and Review
• Barlow Twins: Self-Supervised Learning via Redundancy Reduction
• ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision
• Prototypical Contrastive Learning of Unsupervised Representations
• A Review on Deep Learning in UAV Remote Sensing
• Self-Supervised Representation Learning: Introduction, Advances and Challenges
• Exploring Simple Siamese Representation Learning
• VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
• Hard Negative Mixing for Contrastive Learning
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts
• Self-supervised representation learning from 12-lead ECG data
• SPICE: Semantic Pseudo-labeling for Image Clustering
• Pre-training Molecular Graph Representation with 3D Geometry
• TCLR: Temporal Contrastive Learning for Video Representation
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey
• Twin Contrastive Learning for Online Clustering
• Self-Supervised Learning for Videos: A Survey
• One Million Scenes for Autonomous Driving: ONCE Dataset
• Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
• Learning Representation for Clustering via Prototype Scattering and Positive Sampling
• Disentangling Long and Short-Term Interests for Recommendation
• RaSa: Relation and Sensitivity Aware Representation Learning for Text-based Person Search
• Cluster-guided Asymmetric Contrastive Learning for Unsupervised Person Re-Identification
• Robust High-dimensional Memory-augmented Neural Networks
• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
• Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works
• Learning Self-Supervised Low-Rank Network for Single-Stage Weakly and Semi-Supervised Semantic Segmentation
• Understanding Dimensional Collapse in Contrastive Self-supervised Learning
• Self-Supervised Anomaly Detection in Computer Vision and Beyond: A Survey and Outlook
• Vector-quantized Image Modeling with Improved VQGAN
• COCOA: Cross Modality Contrastive Learning for Sensor Data
• 3D Infomax improves GNNs for Molecular Property Prediction
• Efficient Self-supervised Vision Transformers for Representation Learning
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Spatiotemporal Contrastive Video Representation Learning
• 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
• SEED: Self-supervised Distillation For Visual Representation
• SleePyCo: Automatic Sleep Scoring with Feature Pyramid and Contrastive Learning
• Exploring scalable medical image encoders beyond text supervision
• Self-EMD: Self-Supervised Object Detection without ImageNet
• Self-supervised Learning is More Robust to Dataset Imbalance
• Intriguing Properties of Contrastive Losses
• A Review of Predictive and Contrastive Self-supervised Learning for Medical Images
• Are all negatives created equal in contrastive instance discrimination?
• Federated Contrastive Learning for Volumetric Medical Image Segmentation
• Graph Communal Contrastive Learning
• Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
• Aligning Pretraining for Detection via Object-Level Contrastive Learning
• Learning Off-Road Terrain Traversability with Self-Supervisions Only
• MixCo: Mix-up Contrastive Learning for Visual Representation
• Self-supervised Consensus Representation Learning for Attributed Graph
• Self-Supervision Closes the Gap Between Weak and Strong Supervision in Histology
• The Free Energy Principle for Perception and Action: A Deep Learning Perspective
• Self-supervised Audiovisual Representation Learning for Remote Sensing Data
• Rectifying the Shortcut Learning of Background for Few-Shot Learning
• Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
• A Survey of Visual Transformers
• Whitening for Self-Supervised Representation Learning
• Learning Invariance from Generated Variance for Unsupervised Person Re-identification
• Reinforcement Learning with Prototypical Representations
• ReSSL: Relational Self-Supervised Learning with Weak Augmentation
• Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
• Representation Learning via Invariant Causal Mechanisms
• Support-set bottlenecks for video-text representation learning
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Contrastive Learning with Stronger Augmentations
• Enhancing Network Initialization for Medical AI Models Using Large-Scale, Unlabeled Natural Images
• Understanding Self-supervised Learning with Dual Deep Networks
• MoPro: Webly Supervised Learning with Momentum Prototypes
• UP-DETR: Unsupervised Pre-training for Object Detection with Transformers
• VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning
• PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
• Do Different Tracking Tasks Require Different Appearance Models?
• Cross-Camera Feature Prediction for Intra-Camera Supervised Person Re-identification across Distant Scenes
• Hyperbolic Hierarchical Contrastive Hashing
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
• Information Maximization Clustering via Multi-View Self-Labelling
• A Study of the Generalizability of Self-Supervised Representations
• Meta-learning an Intermediate Representation for Few-shot Block-wise Prediction of Landslide Susceptibility
• Improving COVID-19 CT Classification of CNNs by Learning Parameter-Efficient Representation
• Exploring Cross-Domain Pretrained Model for Hyperspectral Image Classification
• False: False Negative Samples Aware Contrastive Learning for Semantic Segmentation of High-Resolution Remote Sensing Image
• Conditional Negative Sampling for Contrastive Learning of Visual Representations
• X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning
• Incremental False Negative Detection for Contrastive Learning
• Improving colonoscopy lesion classification using semi-supervised deep learning
• A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis
• Self-Supervised Training Enhances Online Continual Learning
• Self-Supervised Learning with Kernel Dependence Maximization
• Revisiting Model Stitching to Compare Neural Representations
• Viewmaker Networks: Learning Views for Unsupervised Representation Learning
• Adaptive Soft Contrastive Learning
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
• BYOL works even without batch statistics
• MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation
• Evaluating Large Language Models as Virtual Annotators for Time-series Physical Sensing Data
• A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
• Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend
• Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
• Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition
• Knowledge Amalgamation for Object Detection with Transformers
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
• Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
• Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution
• Self-supervised Pre-training with Hard Examples Improves Visual Representations
• Motif-Driven Contrastive Learning of Graph Representations
• Clinically Labeled Contrastive Learning for OCT Biomarker Classification
• Universum-inspired Supervised Contrastive Learning
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
• Active Self-Semi-Supervised Learning for Few Labeled Samples
• Mine Your Own vieW: Self-Supervised Learning Through Across-Sample Prediction
• Unsupervised Feature Learning by Cross-Level Instance-Group Discrimination
• Self-supervised Remote Sensing Images Change Detection at Pixel-level
• Modeling Multiple Views via Implicitly Preserving Global Consistency and Local Complementarity
• SSFL: Tackling Label Deficiency in Federated Learning via Personalized Self-Supervision
• Transfer Learning Application of Self-supervised Learning in ARPES
• From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval
• Robust Mutual Learning for Semi-supervised Semantic Segmentation
• AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
• Self-Supervised Features Improve Open-World Learning
• Proxy-based Item Representation for Attribute and Context-aware Recommendation
• Core-set Sampling for Efficient Neural Architecture Search
• Self-supervised Learning from a Multi-view Perspective
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
• Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity
• MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusion
• A Contrastive Learning Approach to Auroral Identification and Classification
• Understand and Improve Contrastive Learning Methods for Visual Representation: A Review
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model
• INTERN: A New Learning Paradigm Towards General Vision
• Prototypical Contrast and Reverse Prediction: Unsupervised Skeleton Based Action Recognition
• Towards Good Practices in Self-supervised Representation Learning
• Spatially Consistent Representation Learning
• Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning
• DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
• Label-Efficient Self-Supervised Speaker Verification With Information Maximization and Contrastive Learning
• Towards Domain-Agnostic Contrastive Learning
• Self-Supervised Learning for Gastritis Detection with Gastric X-ray Images
• RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?
• Boosting multi-demographic federated learning for chest radiograph analysis using general-purpose self-supervised representations
• Learning from Temporal Gradient for Semi-supervised Action Recognition
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision
• SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning
• A Theory of Label Propagation for Subpopulation Shift
• Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
• DisCo: Remedy Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning
• Robust Basket Recommendation via Noise-tolerated Graph Contrastive Learning
• Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Training
• Self-Supervision, Remote Sensing and Abstraction: Representation Learning Across 3 Million Locations
• Understanding Hyperbolic Metric Learning through Hard Negative Sampling
• Self-Supervised Learning for Text Recognition: A Critical Survey
• Augmentation-aware Self-supervised Learning with Conditioned Projector
• A Generic Self-Supervised Framework of Learning Invariant Discriminative Features
• Semantic-Aware Generation for Self-Supervised Visual Representation Learning
• Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation
• Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL
• Unsupervised Object-Level Representation Learning from Scene Images
• Self-Supervised Learning by Estimating Twin Class Distributions
• INoD: Injected Noise Discriminator for Self-Supervised Representation Learning in Agricultural Fields
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Do We Really Need to Learn Representations from In-domain Data for Outlier Detection?
• DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer
• Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
• Representation Learning via Consistent Assignment of Views to Clusters
• Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
• Spatial Ensemble: a Novel Model Smoothing Mechanism for Student-Teacher Framework
• Contrastive Learning and Cycle Consistency-based Transductive Transfer Learning for Target Annotation
• Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning
• Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification Performance
• Self-Supervised Ranking for Representation Learning
• Evaluating the Label Efficiency of Contrastive Self-Supervised Learning for Multi-Resolution Satellite Imagery
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
• Self-supervised Video Representation Learning by Context and Motion Decoupling
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillation
• CUCL: Codebook for Unsupervised Continual Learning
• Interest-oriented Universal User Representation via Contrastive Learning
• Self-supervised visual learning for analyzing firearms trafficking activities on the Web
• Evolutionary Augmentation Policy Optimization for Self-supervised Learning
• MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
• Center-wise Local Image Mixture For Contrastive Representation Learning
• Contrastive Neural Processes for Self-Supervised Learning
• An Empirical Study and Analysis on Open-Set Semi-Supervised Learning
• Self-Supervised Pre-Training Boosts Semantic Scene Segmentation on LiDAR Data
• Simple Distillation Baselines for Improving Small Self-supervised Models
• Self-supervised Representation Learning with Relative Predictive Coding
• On Feature Decorrelation in Self-Supervised Learning
• EqCo: Equivalent Rules for Self-supervised Contrastive Learning
• Contrastive Self-Supervised Learning for Spatio-Temporal Analysis of Lung Ultrasound Videos
• Bag of Tricks and A Strong baseline for Image Copy Detection
• Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning
• Self-Supervised Representation Learning for Nerve Fiber Distribution Patterns in 3D-PLI
• Revisiting the Transferability of Supervised Pretraining: an MLP Perspective
• DREAM: Visual Decoding from Reversing Human Visual System
• Simplicity Bias Leads to Amplified Performance Disparities
• DISCERN: Diversity-based Selection of Centroids for k-Estimation and Rapid Non-stochastic Clustering
• DeepDiffusion: Unsupervised Learning of Retrieval-adapted Representations via Diffusion-based Ranking on Latent Feature Manifold
• Geographical Knowledge-driven Representation Learning for Remote Sensing Images
• Are Fewer Labels Possible for Few-shot Learning?
• Multi-label Iterated Learning for Image Classification with Label Ambiguity
• Unleashing the Potential of Unsupervised Pre-Training with Intra-Identity Regularization for Person Re-Identification
• Unsupervised Part Discovery from Contrastive Reconstruction
• Grounding inductive biases in natural images:invariance stems from variations in data
• Towards Demystifying Representation Learning with Non-contrastive Self-supervision
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
• Pri3D: Can 3D Priors Help 2D Representation Learning?
• Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling
• Self-Supervised Learning for Fine-Grained Visual Categorization
• Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
• Self-Supervised Pretraining on Satellite Imagery: a Case Study on Label-Efficient Vehicle Detection
• Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
• Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
• A Histopathology Study Comparing Contrastive Semi-Supervised and Fully Supervised Learning
• Contrastive Learning for Self-Supervised Pre-Training of Point Cloud Segmentation Networks With Image Data
• Self-Supervised Transformer Architecture for Change Detection in Radio Access Networks
• Meta Clustering Learning for Large-scale Unsupervised Person Re-identification
• Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks
• Leveraging Self-Supervised Vision Transformers for Segmentation-based Transfer Function Design
• Compressive Visual Representations
• Multi-Modality Transformer for E-Commerce: Inferring User Purchase Intention to Bridge the Query-Product Gap
• Long-Short Temporal Contrastive Learning of Video Transformers
• D${}^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection
• PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
• A Style and Semantic Memory Mechanism for Domain Generalization
• Integrating Auxiliary Information in Self-supervised Learning
• Contrastive Learning of Global-Local Video Representations
• Self-Supervised Longitudinal Neighbourhood Embedding
• Contrastive Embeddings for Neural Architectures
• Addressing Feature Suppression in Unsupervised Visual Representations
• A Unified Mixture-View Framework for Unsupervised Representation Learning
• Aggregative Self-Supervised Feature Learning from a Limited Sample
• Instance Selection for GANs
• Towards to Robust and Generalized Medical Image Segmentation Framework
• Multi-level Knowledge Distillation via Knowledge Alignment and Correlation
• Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning
• Multi-dataset Pretraining: A Unified Model for Semantic Segmentation
• Self-Distilled Self-Supervised Representation Learning
• Complementary Relation Contrastive Distillation
• Unsupervised Visual Representation Learning by Online Constrained K-Means
• Information Theory-Guided Heuristic Progressive Multi-View Coding
• Investigating Fine- and Coarse-grained Structural Correspondences Between Deep Neural Networks and Human Object Image Similarity Judgments Using Unsupervised Alignment
• Spherical Sliced-Wasserstein
• eProduct: A Million-Scale Visual Search Benchmark to Address Product Recognition Challenges
• SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency
• Personalizing Pre-trained Models
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• Video Contrastive Learning with Global Context
• Object-Aware Cropping for Self-Supervised Learning
• Exploring Set Similarity for Dense Self-supervised Representation Learning
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
• UniMoCo: Unsupervised, Semi-Supervised and Full-Supervised Visual Representation Learning
• Parametric Contrastive Learning
• Enhancing Stability in Training Conditional Generative Adversarial Networks via Selective Data Matching
• ParamCrop: Parametric Cubic Cropping for Video Contrastive Learning
• Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?
• On the robustness of self-supervised representations for multi-view object classification
• An Efficient Method for the Classification of Croplands in Scarce-Label Regions
• WixUp: A General Data Augmentation Framework for Wireless Perception in Tracking of Humans
• Temporal Knowledge Consistency for Unsupervised Visual Representation Learning
• You Never Cluster Alone
• Unified Framework for Feature Extraction based on Contrastive Learning
• SwAMP: Swapped Assignment of Multi-Modal Pairs for Cross-Modal Retrieval
• Understanding the Role of Self-Supervised Learning in Out-of-Distribution Detection Task
• Stochastic Contrastive Learning
• OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
• Inverse Problems Leveraging Pre-trained Contrastive Representations
• PatchGame: Learning to Signal Mid-level Patches in Referential Games
• SERE: Exploring Feature Self-relation for Self-supervised Transformer
• Recent Advancements in Self-Supervised Paradigms for Visual Feature Representation
• A Survey on Green Deep Learning
• Hybrid BYOL-ViT: Efficient approach to deal with small datasets
• Offline Clustering Approach to Self-supervised Learning for Class-imbalanced Image Data
• PCPs: Patient Cardiac Prototypes
• HoughCL: Finding Better Positive Pairs in Dense Self-supervised Learning
• PreViTS: Contrastive Pretraining with Video Tracking Supervision
• About contrastive unsupervised representation learning for classification and its convergence
• Explicit homography estimation improves contrastive self-supervised learning
• SVMax: A Feature Embedding Regularizer
• Visual Probing: Cognitive Framework for Explaining Self-Supervised Image Representations
• On Compositions of Transformations in Contrastive Self-Supervised Learning
• Vision Pair Learning: An Efficient Training Framework for Image Classification
• ScaleNet: An Unsupervised Representation Learning Method for Limited Information
• Deep Bregman Divergence for Contrastive Learning of Visual Representations
• Learning to Aggregate and Refine Noisy Labels for Visual Sentiment Analysis
• Contrastive Learning of Image Representations with Cross-Video Cycle-Consistency
• Towards Unsupervised Sketch-based Image Retrieval
• Online Unsupervised Learning of Visual Representations and Categories
• GraphVICRegHSIC: Towards improved self-supervised representation learning for graphs with a hyrbid loss function
• MC-SSL0.0: Towards Multi-Concept Self-Supervised Learning
• Data-Driven Self-Supervised Graph Representation Learning
• Transferrable Contrastive Learning for Visual Domain Adaptation
• Domain-Agnostic Clustering with Self-Distillation
• EEG-Driven Image Reconstruction with Saliency-Guided Diffusion Models
• Self-Supervised Learning for Large-Scale Unsupervised Image Clustering
• Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning
• Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
• UCSL : A Machine Learning Expectation-Maximization framework for Unsupervised Clustering driven by Supervised Learning
• Characterizing and Improving the Robustness of Self-Supervised Learning through Background Augmentations
• Improve Unsupervised Pretraining for Few-label Transfer
• Batch Curation for Unsupervised Contrastive Representation Learning
• On-target Adaptation
• Seeking an Optimal Approach for Computer-Aided Pulmonary Embolism Detection
• Learning Deep Representation with Energy-Based Self-Expressiveness for Subspace Clustering
• Self-Supervised Neural Architecture Search for Imbalanced Datasets
• Homography augumented momentum constrastive learning for SAR image retrieval
• CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations
• Three Pillars improving Vision Foundation Model Distillation for Lidar
• GenURL: A General Framework for Unsupervised Representation Learning
• Learning Rich Nearest Neighbor Representations from Self-supervised Ensembles