Prototypical Networks for Few-shot Learning

Abstract

We propose prototypical networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class. Prototypical networks learn a metric space in which classification can be performed by computing distances to prototype representations of each class. Compared to recent approaches for few-shot learning, they reflect a simpler inductive bias that is beneficial in this limited-data regime, and achieve excellent results. We provide an analysis showing that some simple design decisions can yield substantial improvements over recent approaches involving complicated architectural choices and meta-learning. We further extend prototypical networks to zero-shot learning and achieve state-of-the-art results on the CU-Birds dataset.

Cited by in corpus (1221)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• On the Opportunities and Risks of Foundation Models
• Recent Advances in Open Set Recognition: A Survey
• COVID-19 Image Data Collection: Prospective Predictions Are the Future
• Generalizing from a Few Examples: A Survey on Few-Shot Learning
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Social physics
• Prototypical Contrastive Learning of Unsupervised Representations
• Few-Shot Learning with Graph Neural Networks
• In defence of metric learning for speaker recognition
• Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
• A Survey: Deep Learning for Hyperspectral Image Classification with Few Labeled Samples
• Frustratingly Simple Few-Shot Object Detection
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• LEAF: A Benchmark for Federated Settings
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Self-supervised learning methods and applications in medical imaging analysis: A survey
• FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation
• SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning
• Learning to Self-Train for Semi-Supervised Few-Shot Classification
• Decoupling Representation and Classifier for Long-Tailed Recognition
• BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classification
• ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection
• DoFE: Domain-oriented Feature Embedding for Generalizable Fundus Image Segmentation on Unseen Datasets
• Meta-Learning with Latent Embedding Optimization
• Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classification
• Few-shot classification in Named Entity Recognition Task
• TADAM: Task dependent adaptive metric for improved few-shot learning
• True Few-Shot Learning with Language Models
• Momentum Contrastive Learning for Few-Shot COVID-19 Diagnosis from Chest CT Images
• A Closer Look at Few-shot Classification
• Free Lunch for Few-shot Learning: Distribution Calibration
• Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
• Meta-Reinforcement Learning of Structured Exploration Strategies
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxels
• Unsupervised Learning via Meta-Learning
• Piecewise classifier mappings: Learning fine-grained learners for novel categories with few examples
• Bayesian Model-Agnostic Meta-Learning
• A Two-Stage Approach to Few-Shot Learning for Image Recognition
• Automated Machine Learning: State-of-The-Art and Open Challenges
• Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
• Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks
• Meta-learning with differentiable closed-form solvers
• Few-shot Object Detection on Remote Sensing Images
• An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learning
• Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
• PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling
• Interventional Few-Shot Learning
• Abstraction and Analogy-Making in Artificial Intelligence
• Federated Continual Learning via Knowledge Fusion: A Survey
• Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
• Robust High-dimensional Memory-augmented Neural Networks
• Transformer with Peak Suppression and Knowledge Guidance for Fine-grained Image Recognition
• MetaKG: Meta-learning on Knowledge Graph for Cold-start Recommendation
• Contrastive Cross-Domain Sequential Recommendation
• Bilevel Programming for Hyperparameter Optimization and Meta-Learning
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
• Dataset Condensation with Gradient Matching
• Incremental Object Detection via Meta-Learning
• Leveraging the Invariant Side of Generative Zero-Shot Learning
• Deep Meta-Learning: Learning to Learn in the Concept Space
• Few-Shot Segmentation Propagation with Guided Networks
• Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
• Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
• Spatio-Temporal Graph Few-Shot Learning with Cross-City Knowledge Transfer
• Self-Supervised Generalisation with Meta Auxiliary Learning
• A review on vision-based analysis for automatic dietary assessment
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
• Towards a universal neural network encoder for time series
• Meta-Learning Update Rules for Unsupervised Representation Learning
• TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition
• TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samples
• Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions
• Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
• KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
• Few-Shot Unsupervised Image-to-Image Translation
• DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
• Adaptation Algorithms for Neural Network-Based Speech Recognition: An Overview
• Deep Long-Tailed Learning: A Survey
• Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation
• Neuron Linear Transformation: Modeling the Domain Shift for Crowd Counting
• Semi-supervised Domain Adaptation via Minimax Entropy
• Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples
• In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning
• Feature-Critic Networks for Heterogeneous Domain Generalization
• Dynamic Few-Shot Visual Learning without Forgetting
• Self-supervised Knowledge Distillation for Few-shot Learning
• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
• Few-Shot Learning with Geometric Constraints
• Test-Time Training with Self-Supervision for Generalization under Distribution Shifts
• Accurate Learning of Graph Representations with Graph Multiset Pooling
• Meta-Learning with Warped Gradient Descent
• Low-Shot Learning from Imaginary Data
• One-Shot Instance Segmentation
• Large-Scale Long-Tailed Recognition in an Open World
• Hyperspherical Prototype Networks
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• Meta-learning for Few-shot Natural Language Processing: A Survey
• Bayesian Meta-Learning for the Few-Shot Setting via Deep Kernels
• BOIL: Towards Representation Change for Few-shot Learning
• Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data
• Gaussian Prototypical Networks for Few-Shot Learning on Omniglot
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
• CrossTransformers: spatially-aware few-shot transfer
• Multi-level Second-order Few-shot Learning
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• A Universal Representation Transformer Layer for Few-Shot Image Classification
• A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
• On Warm-Starting Neural Network Training
• Hypercorrelation Squeeze for Few-Shot Segmentation
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
• Few-shot Text Classification with Distributional Signatures
• MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation
• Facilitating Knowledge Sharing from Domain Experts to Data Scientists for Building NLP Models
• Unsupervised Meta-Learning for Reinforcement Learning
• Efficient Few-Shot Object Detection via Knowledge Inheritance
• Alpha MAML: Adaptive Model-Agnostic Meta-Learning
• Conditional Neural Processes
• Few-Shot Named Entity Recognition: A Comprehensive Study
• Out of Distribution Generalization in Machine Learning
• tax2vec: Constructing Interpretable Features from Taxonomies for Short Text Classification
• Adaptive Siamese Tracking with a Compact Latent Network
• Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• FedBABU: Towards Enhanced Representation for Federated Image Classification
• Transductive Information Maximization For Few-Shot Learning
• MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• Relational Knowledge Distillation
• Self-Augmentation: Generalizing Deep Networks to Unseen Classes for Few-Shot Learning
• Meta-Learning Requires Meta-Augmentation
• ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users
• Mask-guided BERT for Few Shot Text Classification
• Rectifying the Shortcut Learning of Background for Few-Shot Learning
• CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
• Continual Learning and Catastrophic Forgetting
• A Survey of Optimization Methods from a Machine Learning Perspective
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
• A Survey on Open Set Recognition
• Compositional generalization through meta sequence-to-sequence learning
• Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
• Subspace Regularizers for Few-Shot Class Incremental Learning
• Why is the Mahalanobis Distance Effective for Anomaly Detection?
• Adversarially Robust Few-Shot Learning: A Meta-Learning Approach
• Zero-shot Node Classification with Decomposed Graph Prototype Network
• Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
• Leveraging Siamese Networks for One-Shot Intrusion Detection Model
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention Mechanisms
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learning
• Prototypical Representation Learning for Relation Extraction
• Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector
• Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
• Learning from Few Samples: A Survey
• Neural Data Augmentation via Example Extrapolation
• MHFC: Multi-Head Feature Collaboration for Few-Shot Learning
• Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation
• A Comprehensive Overview and Survey of Recent Advances in Meta-Learning
• Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
• Multimodal Parameter-Efficient Few-Shot Class Incremental Learning
• Grounded Language Learning Fast and Slow
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
• Few-Shot Keyword Spotting in Any Language
• Structured Prediction as Translation between Augmented Natural Languages
• Few-shot Action Recognition with Prototype-centered Attentive Learning
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
• Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation
• CG-BERT: Conditional Text Generation with BERT for Generalized Few-shot Intent Detection
• TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition
• Deep Weakly-supervised Anomaly Detection
• Online Hyperparameter Optimization for Class-Incremental Learning
• Few Shot Speaker Recognition using Deep Neural Networks
• Provable Guarantees for Gradient-Based Meta-Learning
• Prior-Knowledge and Attention-based Meta-Learning for Few-Shot Learning
• Meta-learning of Sequential Strategies
• AVA-AVD: Audio-Visual Speaker Diarization in the Wild
• Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
• Negative Margin Matters: Understanding Margin in Few-shot Classification
• The Functional Neural Process
• Self-Supervised Learning for Domain Adaptation on Point-Clouds
• Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data
• Meta-Transfer Learning for Few-Shot Learning
• Deep Triplet Ranking Networks for One-Shot Recognition
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Few-Shot Keyword Spotting With Prototypical Networks
• Leveraging the Feature Distribution in Transfer-based Few-Shot Learning
• Deep learning based infrared small object segmentation: Challenges and future directions
• Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning
• Few-Shot Segmentation via Cycle-Consistent Transformer
• TaskNorm: Rethinking Batch Normalization for Meta-Learning
• Revisiting Fine-tuning for Few-shot Learning
• Incremental Few-Shot Learning with Attention Attractor Networks
• Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networks
• Long-tailed Recognition by Routing Diverse Distribution-Aware Experts
• Edge-labeling Graph Neural Network for Few-shot Learning
• BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
• Meta-Graph: Few Shot Link Prediction via Meta Learning
• FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
• Optimized Generic Feature Learning for Few-shot Classification across Domains
• Example-Based Named Entity Recognition
• Prediction Calibration for Generalized Few-shot Semantic Segmentation
• Controllable Semantic Parsing via Retrieval Augmentation
• Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognition
• Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples
• Meta-Learned Confidence for Few-shot Learning
• The Variational Homoencoder: Learning to learn high capacity generative models from few examples
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Federated Few-Shot Learning for Mobile NLP
• Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning
• Meta-Learning for Low-Resource Neural Machine Translation
• Improved Schemes for Episodic Memory-based Lifelong Learning
• Adversarial Meta-Learning
• Attentive Neural Processes
• Episodic Training for Domain Generalization
• Meta-Consolidation for Continual Learning
• Few-Shot Learning with Global Class Representations
• Defining Benchmarks for Continual Few-Shot Learning
• Data Augmentation for Meta-Learning
• GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning
• Prototype Mixture Models for Few-shot Semantic Segmentation
• Feature Transfer Learning for Deep Face Recognition with Under-Represented Data
• Self-Supervised Learning For Few-Shot Image Classification
• Part-aware Prototype Network for Few-shot Semantic Segmentation
• Automated Human Cell Classification in Sparse Datasets using Few-Shot Learning
• Federated Model Distillation with Noise-Free Differential Privacy
• Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters
• Prototype Guided Federated Learning of Visual Feature Representations
• A Closer Look at Few-Shot 3D Point Cloud Classification
• Restoring Negative Information in Few-Shot Object Detection
• Auto-Meta: Automated Gradient Based Meta Learner Search
• Diverse Few-Shot Text Classification with Multiple Metrics
• Improved Meta Learning for Low Resource Speech Recognition
• Concept Learning through Deep Reinforcement Learning with Memory-Augmented Neural Networks
• TGDM: Target Guided Dynamic Mixup for Cross-Domain Few-Shot Learning
• Cross-Domain Few-Shot Learning by Representation Fusion
• Task-Robust Model-Agnostic Meta-Learning
• Meta-DETR: Image-Level Few-Shot Object Detection with Inter-Class Correlation Exploitation
• DPGN: Distribution Propagation Graph Network for Few-shot Learning
• Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
• A Prototype-Oriented Framework for Unsupervised Domain Adaptation
• RP2K: A Large-Scale Retail Product Dataset for Fine-Grained Image Classification
• Probabilistic Model-Agnostic Meta-Learning
• Families In Wild Multimedia: A Multimodal Database for Recognizing Kinship
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Weakly-supervised Compositional FeatureAggregation for Few-shot Recognition
• Node Classification on Graphs with Few-Shot Novel Labels via Meta Transformed Network Embedding
• Meta-Learning Symmetries by Reparameterization
• Independent Prototype Propagation for Zero-Shot Compositionality
• Image Deformation Meta-Networks for One-Shot Learning
• ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning
• Adversarial Feature Hallucination Networks for Few-Shot Learning
• Large Margin Few-Shot Learning
• Prototype Refinement Network for Few-Shot Segmentation
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
• Robust MAML: Prioritization task buffer with adaptive learning process for model-agnostic meta-learning
• Task Augmentation by Rotating for Meta-Learning
• DAWSON: A Domain Adaptive Few Shot Generation Framework
• Penalty Method for Inversion-Free Deep Bilevel Optimization
• General stochastic separation theorems with optimal bounds
• Automated Relational Meta-learning
• Optimal Transport Graph Neural Networks
• Sill-Net: Feature Augmentation with Separated Illumination Representation
• Bias-Eliminated Semantic Refinement for Any-Shot Learning
• Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning
• Adaptive Gradient-Based Meta-Learning Methods
• A Baseline for Few-Shot Image Classification
• Learning to Discover Novel Visual Categories via Deep Transfer Clustering
• Few-Shot Learning via Saliency-guided Hallucination of Samples
• Meta-Learning for Few-Shot Land Cover Classification
• Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
• Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
• Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
• MetaIQA: Deep Meta-learning for No-Reference Image Quality Assessment
• Locality and compositionality in zero-shot learning
• All About Knowledge Graphs for Actions
• Backdoor Attacks on Federated Meta-Learning
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• Domain Adaptive Dialog Generation via Meta Learning
• Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
• MobilePhys: Personalized Mobile Camera-Based Contactless Physiological Sensing
• Geometer: Graph Few-Shot Class-Incremental Learning via Prototype Representation
• Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference
• Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels
• LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
• CRNet: Cross-Reference Networks for Few-Shot Segmentation
• Explanation-Guided Training for Cross-Domain Few-Shot Classification
• Cross-Lingual Speaker Verification with Domain-Balanced Hard Prototype Mining and Language-Dependent Score Normalization
• Cross-domain Object Detection through Coarse-to-Fine Feature Adaptation
• Transferring Cross-domain Knowledge for Video Sign Language Recognition
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• Image-to-Image Translation: Methods and Applications
• Few-Shot Incremental Learning with Continually Evolved Classifiers
• Metric-Based Few-Shot Learning for Video Action Recognition
• Semi-Supervised Visual Representation Learning for Fashion Compatibility
• Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
• Enhancing Few-shot Image Classification with Cosine Transformer
• A dual-branch model with inter- and intra-branch contrastive loss for long-tailed recognition
• Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation
• On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction
• Learning to Learn Variational Semantic Memory
• Few-Shot Speaker Identification Using Lightweight Prototypical Network with Feature Grouping and Interaction
• One-Shot Object Detection without Fine-Tuning
• RelationNet2: Deep Comparison Columns for Few-Shot Learning
• Cross-modal Hallucination for Few-shot Fine-grained Recognition
• Ultra Efficient Transfer Learning with Meta Update for Cross Subject EEG Classification
• Comparison Network for One-Shot Conditional Object Detection
• Self-training for Few-shot Transfer Across Extreme Task Differences
• One-Shot Relational Learning for Knowledge Graphs
• Debiased Contrastive Learning
• MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
• Image Based Identification of Ghanaian Timbers Using the XyloTron: Opportunities, Risks and Challenges
• Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
• TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
• Few-shot Action Recognition with Permutation-invariant Attention
• Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks
• Truncated Back-propagation for Bilevel Optimization
• Adaptive Deep Kernel Learning
• Wandering Within a World: Online Contextualized Few-Shot Learning
• DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection
• A Broader Study of Cross-Domain Few-Shot Learning
• Revisiting Meta-Learning as Supervised Learning
• Max-margin Class Imbalanced Learning with Gaussian Affinity
• Transfer Learning for Estimating Causal Effects using Neural Networks
• Towards Cross-Granularity Few-Shot Learning: Coarse-to-Fine Pseudo-Labeling with Visual-Semantic Meta-Embedding
• How to Train Your MAML to Excel in Few-Shot Classification
• Identifying Unknown Instances for Autonomous Driving
• Induction Networks for Few-Shot Text Classification
• When MAML Can Adapt Fast and How to Assist When It Cannot
• Relational Generalized Few-Shot Learning
• Few-shot Object Detection via Feature Reweighting
• Learning Dynamic Alignment via Meta-filter for Few-shot Learning
• Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems
• Meta Discovery: Learning to Discover Novel Classes given Very Limited Data
• Few-Shot Video Classification via Temporal Alignment
• Minimax Active Learning
• On Episodes, Prototypical Networks, and Few-shot Learning
• Joint Noise-Tolerant Learning and Meta Camera Shift Adaptation for Unsupervised Person Re-Identification
• Episode-based Prototype Generating Network for Zero-Shot Learning
• When Does Self-supervision Improve Few-shot Learning?
• Adaptive Masked Proxies for Few-Shot Segmentation
• ProtoAttend: Attention-Based Prototypical Learning
• Prototype Rectification for Few-Shot Learning
• KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences
• Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
• COVID-Net USPro: An Open-Source Explainable Few-Shot Deep Prototypical Network to Monitor and Detect COVID-19 Infection from Point-of-Care Ultrasound Images
• Few-shot Image Generation via Cross-domain Correspondence
• Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
• Model-based Adversarial Meta-Reinforcement Learning
• Multi-scale Adaptive Task Attention Network for Few-Shot Learning
• Semantic Drift Compensation for Class-Incremental Learning
• Few-Shot Class-Incremental Learning
• Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation
• PixelVAE++: Improved PixelVAE with Discrete Prior
• Universal Semi-Supervised Semantic Segmentation
• Embedding Learning in Hybrid Quantum-Classical Neural Networks
• Leveraging Class Hierarchies with Metric-Guided Prototype Learning
• Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• Lightweight Speaker Verification for Online Identification of New Speakers with Short Segments
• Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis
• A Comparative Review of Recent Few-Shot Object Detection Algorithms
• Unsupervised Few-shot Learning via Self-supervised Training
• Dynamic Relevance Learning for Few-Shot Object Detection
• Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation
• A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
• Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
• Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
• GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
• Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
• Meta-Learning for Short Utterance Speaker Recognition with Imbalance Length Pairs
• Few-Shot Action Recognition with Compromised Metric via Optimal Transport
• Metric Learning vs Classification for Disentangled Music Representation Learning
• MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters
• Few-Shot Learning for Road Object Detection
• Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning
• Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
• A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
• FewJoint: A Few-shot Learning Benchmark for Joint Language Understanding
• ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
• Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning
• Few-shot Classification via Adaptive Attention
• Discovering New Intents via Constrained Deep Adaptive Clustering with Cluster Refinement
• Dynamic backdoor attacks against federated learning
• LibFewShot: A Comprehensive Library for Few-shot Learning
• Few-Shot Learning with Uncertainty-based Quadruplet Selection for Interference Classification in GNSS Data
• Demonstrating Mobile Manipulation in the Wild: A Metrics-Driven Approach
• Few-shot Learning for Time-series Forecasting
• SMIL: Multimodal Learning with Severely Missing Modality
• Towards Understanding Generalization in Gradient-Based Meta-Learning
• Sequential Scenario-Specific Meta Learner for Online Recommendation
• TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learning
• Distance-Based Learning from Errors for Confidence Calibration
• KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
• Interpretable Medical Image Classification using Prototype Learning and Privileged Information
• BeamSense: Rethinking Wireless Sensing with MU-MIMO Wi-Fi Beamforming Feedback
• p-Meta: Towards On-device Deep Model Adaptation
• A Closer Look at Prototype Classifier for Few-shot Image Classification
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
• Fixed-MAML for Few Shot Classification in Multilingual Speech Emotion Recognition
• Improving Generalization in Meta-learning via Task Augmentation
• Selecting Relevant Features from a Multi-domain Representation for Few-shot Classification
• Meta-Learning across Meta-Tasks for Few-Shot Learning
• A Meta-Learning Framework for Generalized Zero-Shot Learning
• A Theoretical Analysis of the Number of Shots in Few-Shot Learning
• Deep Metric Transfer for Label Propagation with Limited Annotated Data
• Reconciling meta-learning and continual learning with online mixtures of tasks
• Learning to Augment Expressions for Few-shot Fine-grained Facial Expression Recognition
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
• Memory-Based Graph Networks
• Learning to learn via Self-Critique
• Isometric Propagation Network for Generalized Zero-shot Learning
• Hallucination Improves Few-Shot Object Detection
• Personalized Federated Learning with Gaussian Processes
• Graph Meta Learning via Local Subgraphs
• How Important is the Train-Validation Split in Meta-Learning?
• Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
• Learning to Learn with Variational Information Bottleneck for Domain Generalization
• When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification
• Hyperbolic Deep Neural Networks: A Survey
• MetaPhys: Few-Shot Adaptation for Non-Contact Physiological Measurement
• openFEAT: Improving Speaker Identification by Open-set Few-shot Embedding Adaptation with Transformer
• Meta-Learning with Fewer Tasks through Task Interpolation
• Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
• One-shot Texture Segmentation
• Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
• Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms
• E${}^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
• Centroid-based deep metric learning for speaker recognition
• Stochastic Prototype Embeddings
• StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval
• Uncertainty in Multitask Transfer Learning
• Contrastive-mixup learning for improved speaker verification
• Region Comparison Network for Interpretable Few-shot Image Classification
• End-to-end Deep Prototype and Exemplar Models for Predicting Human Behavior
• Shaping Visual Representations with Attributes for Few-Shot Recognition
• Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data
• Blessing of dimensionality at the edge
• L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout
• Variational Prototype Replays for Continual Learning
• Document-Level Event Argument Extraction by Conditional Generation
• SLEEPER: interpretable Sleep staging via Prototypes from Expert Rules
• Adversarial Motorial Prototype Framework for Open Set Recognition
• SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
• Improving Generalization via Scalable Neighborhood Component Analysis
• Learning to Synthesize Programs as Interpretable and Generalizable Policies
• Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
• FGN: Fully Guided Network for Few-Shot Instance Segmentation
• Similarity R-C3D for Few-shot Temporal Activity Detection
• Few-Shot Viewpoint Estimation
• Modularity in Deep Learning: A Survey
• An Investigation of Few-Shot Learning in Spoken Term Classification
• Weak-shot Fine-grained Classification via Similarity Transfer
• Instance Credibility Inference for Few-Shot Learning
• Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
• Zero-Shot Learning from scratch (ZFS): leveraging local compositional representations
• Zero-shot Relation Classification from Side Information
• Dual-Awareness Attention for Few-Shot Object Detection
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification
• Revisiting Few-shot Activity Detection with Class Similarity Control
• One-Shot GAN Generated Fake Face Detection
• Stateless Neural Meta-Learning using Second-Order Gradients
• Weighted Meta-Learning
• OntoED: Low-resource Event Detection with Ontology Embedding
• Mutual exclusivity as a challenge for deep neural networks
• Continuous Meta-Learning without Tasks
• Task-Aware Feature Generation for Zero-Shot Compositional Learning
• Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• MetaFun: Meta-Learning with Iterative Functional Updates
• Few-shot Unsupervised Domain Adaptation with Image-to-class Sparse Similarity Encoding
• Cross-domain Few-shot Learning with Task-specific Adapters
• Proposal-based Few-shot Sound Event Detection for Speech and Environmental Sounds with Perceivers
• Few-Shot Drum Transcription in Polyphonic Music
• Learning a Universal Template for Few-shot Dataset Generalization
• Meta Reinforcement Learning with Task Embedding and Shared Policy
• Imbalanced Continual Learning with Partitioning Reservoir Sampling
• Context-Aware Visual Compatibility Prediction
• Boosting Few-Shot Learning With Adaptive Margin Loss
• Few-Shot Learning as Domain Adaptation: Algorithm and Analysis
• Representation based meta-learning for few-shot spoken intent recognition
• Distance-wise Prototypical Graph Neural Network in Node Imbalance Classification
• Variational Prototyping-Encoder: One-Shot Learning with Prototypical Images
• Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network
• Training speaker recognition systems with limited data
• Meta-Amortized Variational Inference and Learning
• Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark
• Attribute Propagation Network for Graph Zero-shot Learning
• Bayesian Few-Shot Classification with One-vs-Each Pólya-Gamma Augmented Gaussian Processes
• Redefining DDoS Attack Detection Using A Dual-Space Prototypical Network-Based Approach
• Is Support Set Diversity Necessary for Meta-Learning?
• Online Structured Meta-learning
• A Novel Generative Multi-Task Representation Learning Approach for Predicting Postoperative Complications in Cardiac Surgery Patients
• Unbiased Evaluation of Deep Metric Learning Algorithms
• ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning
• Learning Robust Correlation with Foundation Model for Weakly-Supervised Few-Shot Segmentation
• Cross-Domain Adaptation for Animal Pose Estimation
• Curriculum in Gradient-Based Meta-Reinforcement Learning
• Multi-Objective Meta Learning
• Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learning
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Learning a Prior over Intent via Meta-Inverse Reinforcement Learning
• Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
• ProtoTransformer: A Meta-Learning Approach to Providing Student Feedback
• Guiding Policies with Language via Meta-Learning
• MetaPred: Meta-Learning for Clinical Risk Prediction with Limited Patient Electronic Health Records
• ARCADe: A Rapid Continual Anomaly Detector
• Emergent Communication of Generalizations
• Meta-Learning-Based Robust Adaptive Flight Control Under Uncertain Wind Conditions
• Adaptive Consistency Regularization for Semi-Supervised Transfer Learning
• AHA! an 'Artificial Hippocampal Algorithm' for Episodic Machine Learning
• Probabilistic Active Meta-Learning
• Learning to Learn Single Domain Generalization
• Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning
• A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
• Domain Attention Consistency for Multi-Source Domain Adaptation
• Learning from Adversarial Features for Few-Shot Classification
• Leveraging Bottom-Up and Top-Down Attention for Few-Shot Object Detection
• Low-Shot Learning with Imprinted Weights
• Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extraction
• MM-FSOD: Meta and metric integrated few-shot object detection
• Proxy Anchor Loss for Deep Metric Learning
• Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge
• Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
• Data-Efficient Mutual Information Neural Estimator
• Task-similarity Aware Meta-learning through Nonparametric Kernel Regression
• Semi-Supervised Few-Shot Intent Classification and Slot Filling
• TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learning
• XtarNet: Learning to Extract Task-Adaptive Representation for Incremental Few-Shot Learning
• Structured Prediction for Conditional Meta-Learning
• A Real-time Robot-based Auxiliary System for Risk Evaluation of COVID-19 Infection
• Few-shot learning with attention-based sequence-to-sequence models
• Prototypical Clustering Networks for Dermatological Disease Diagnosis
• Measuring Dataset Granularity
• Few-Shot Representation Learning for Out-Of-Vocabulary Words
• Revisiting Few-Shot Learning for Facial Expression Recognition
• Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess
• PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction
• SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems
• LaSO: Label-Set Operations networks for multi-label few-shot learning
• On Sequential Bayesian Inference for Continual Learning
• Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction
• Label-Efficient Object Detection via Region Proposal Network Pre-Training
• MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• MCML: A Novel Memory-based Contrastive Meta-Learning Method for Few Shot Slot Tagging
• Few-Shot Sequence Labeling with Label Dependency Transfer and Pair-wise Embedding
• Meta-learning algorithms for Few-Shot Computer Vision
• OpenNRE: An Open and Extensible Toolkit for Neural Relation Extraction
• Detecting Human-Object Interaction via Fabricated Compositional Learning
• Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition
• Neural Snowball for Few-Shot Relation Learning
• Open Set Chinese Character Recognition using Multi-typed Attributes
• Prototype-based Incremental Few-Shot Semantic Segmentation
• Learning from scarce information: using synthetic data to classify Roman fine ware pottery
• Towards Learning Affine-Invariant Representations via Data-Efficient CNNs
• A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation
• Prototype Completion with Primitive Knowledge for Few-Shot Learning
• Pre-training Text Representations as Meta Learning
• Exemplar Auditing for Multi-Label Biomedical Text Classification
• Comparison-Based Convolutional Neural Networks for Cervical Cell/Clumps Detection in the Limited Data Scenario
• Prototypical Q Networks for Automatic Conversational Diagnosis and Few-Shot New Disease Adaption
• Fine-Grain Few-Shot Vision via Domain Knowledge as Hyperspherical Priors
• PARN: Position-Aware Relation Networks for Few-Shot Learning
• Few-shot Slot Tagging with Collapsed Dependency Transfer and Label-enhanced Task-adaptive Projection Network
• MetaMixUp: Learning Adaptive Interpolation Policy of MixUp with Meta-Learning
• Dynamic Memory Induction Networks for Few-Shot Text Classification
• Few-Shot Electronic Health Record Coding through Graph Contrastive Learning
• Generalized Adaptation for Few-Shot Learning
• Meta-Learning with Adaptive Hyperparameters
• ClusterFit: Improving Generalization of Visual Representations
• Dataset Meta-Learning from Kernel Ridge-Regression
• Automatic Learning to Detect Concept Drift
• Differentiable Meta-learning Model for Few-shot Semantic Segmentation
• Few-Shot Knowledge Graph Completion
• Attentive Graph Neural Networks for Few-Shot Learning
• Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders
• NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification
• Few-shot Open-set Recognition by Transformation Consistency
• Texture Bias Of CNNs Limits Few-Shot Classification Performance
• Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem
• ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning
• Heuristic-free Optimization of Force-Controlled Robot Search Strategies in Stochastic Environments
• GPU-based Self-Organizing Maps for Post-Labeled Few-Shot Unsupervised Learning
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning
• Few-shot Object Grounding and Mapping for Natural Language Robot Instruction Following
• Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation
• Weakly-supervised Object Localization for Few-shot Learning and Fine-grained Few-shot Learning
• Domain Generalization via Semi-supervised Meta Learning
• AgileNet: Lightweight Dictionary-based Few-shot Learning
• Regularizing Meta-Learning via Gradient Dropout
• Interpreting Neural Networks Using Flip Points
• Bowtie Networks: Generative Modeling for Joint Few-Shot Recognition and Novel-View Synthesis
• Bipartite Graph Embedding via Mutual Information Maximization
• Learning Meta Face Recognition in Unseen Domains
• Towards Generalized and Incremental Few-Shot Object Detection
• Attention-based multi-channel speaker verification with ad-hoc microphone arrays
• Domain-Specific Priors and Meta Learning for Few-Shot First-Person Action Recognition
• Prototype Memory for Large-scale Face Representation Learning
• Generalized Zero and Few-Shot Transfer for Facial Forgery Detection
• Domain-Adaptive Few-Shot Learning
• Semi-Supervised Few-Shot Learning with Prototypical Random Walks
• Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings
• Multiple Meta-model Quantifying for Medical Visual Question Answering
• Feed-Forward Neural Networks Need Inductive Bias to Learn Equality Relations
• Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
• Learning to Learn in a Semi-Supervised Fashion
• Embedding Adaptation is Still Needed for Few-Shot Learning
• Graph Few-shot Learning via Knowledge Transfer
• FewRel 2.0: Towards More Challenging Few-Shot Relation Classification
• Few-shot Sequence Learning with Transformers
• Making Good on LSTMs' Unfulfilled Promise
• Boosting Supervision with Self-Supervision for Few-shot Learning
• CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Community
• Incremental Few-Shot Learning for Pedestrian Attribute Recognition
• Learning Relation Prototype from Unlabeled Texts for Long-tail Relation Extraction
• Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
• Meta-Learning Dynamics Forecasting Using Task Inference
• Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection
• Adaptive Task Sampling for Meta-Learning
• Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
• Few-Shot Open-Set Recognition using Meta-Learning
• Few-shot tweet detection in emerging disaster events
• MetaDelta: A Meta-Learning System for Few-shot Image Classification
• Formalizing the Generalization-Forgetting Trade-off in Continual Learning
• Continual egocentric object recognition
• Cross-Modulation Networks for Few-Shot Learning
• Few-NERD: A Few-Shot Named Entity Recognition Dataset
• Rectified Meta-Learning from Noisy Labels for Robust Image-based Plant Disease Diagnosis
• CURI: A Benchmark for Productive Concept Learning Under Uncertainty
• Meta Learning Black-Box Population-Based Optimizers
• Learning to Transfer: Unsupervised Meta Domain Translation
• How Fine-Tuning Allows for Effective Meta-Learning
• Compositional Few-Shot Recognition with Primitive Discovery and Enhancing
• The Role of Global Labels in Few-Shot Classification and How to Infer Them
• Neural Complexity Measures
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
• Embedding Transfer with Label Relaxation for Improved Metric Learning
• Hyperbolic Busemann Learning with Ideal Prototypes
• Learning Task-General Representations with Generative Neuro-Symbolic Modeling
• MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction
• Chameleon: Learning Model Initializations Across Tasks With Different Schemas
• Composed Variational Natural Language Generation for Few-shot Intents
• Information Theoretic Meta Learning with Gaussian Processes
• Instance Cross Entropy for Deep Metric Learning
• Deep Anomaly Detection with Deviation Networks
• Adversarial Reweighting for Speaker Verification Fairness
• Meta Learning for Few-Shot One-class Classification
• A Plug-in Method for Representation Factorization in Connectionist Models
• The Tensor Brain: Semantic Decoding for Perception and Memory
• Adaptive Cross-Modal Few-Shot Learning
• PAC-Bayes Bounds for Meta-learning with Data-Dependent Prior
• MxML: Mixture of Meta-Learners for Few-Shot Classification
• FLEX: Unifying Evaluation for Few-Shot NLP
• Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillance
• Large Margin Mechanism and Pseudo Query Set on Cross-Domain Few-Shot Learning
• Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study
• Ranked List Loss for Deep Metric Learning
• GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition
• Multi-Level Correlation Network For Few-Shot Image Classification
• Multilingual Speech Recognition using Knowledge Transfer across Learning Processes
• FLAT: Few-Shot Learning via Autoencoding Transformation Regularizers
• Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
• Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification
• Does Head Label Help for Long-Tailed Multi-Label Text Classification
• Self-mentoring: a new deep learning pipeline to train a self-supervised U-net for few-shot learning of bio-artificial capsule segmentation
• Meta-Learning with Neural Tangent Kernels
• Entity Concept-enhanced Few-shot Relation Extraction
• Ranking Distance Calibration for Cross-Domain Few-Shot Learning
• Human and Scene Motion Deblurring using Pseudo-blur Synthesizer
• Meta-Learning to Cluster
• PointMixup: Augmentation for Point Clouds
• Meta-Learning 3D Shape Segmentation Functions
• Learning Prototype-oriented Set Representations for Meta-Learning
• Continual Local Replacement for Few-shot Learning
• An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality
• Regression Networks for Meta-Learning Few-Shot Classification
• SCHA-VAE: Hierarchical Context Aggregation for Few-Shot Generation
• On the Importance of Firth Bias Reduction in Few-Shot Classification
• Semi-Supervised and Active Few-Shot Learning with Prototypical Networks
• Meta Dropout: Learning to Perturb Features for Generalization
• Sign-MAML: Efficient Model-Agnostic Meta-Learning by SignSGD
• Learning Oculomotor Behaviors from Scanpath
• Concept Learners for Few-Shot Learning
• MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection
• DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data
• Generating Personalized Dialogue via Multi-Task Meta-Learning
• A Channel Coding Benchmark for Meta-Learning
• Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
• Attentional Prototype Inference for Few-Shot Segmentation
• Few-Shot Learning by Integrating Spatial and Frequency Representation
• Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
• Revisiting Metric Learning for Few-Shot Image Classification
• Universal Natural Language Processing with Limited Annotations: Try Few-shot Textual Entailment as a Start
• Distributional Robustness Loss for Long-tail Learning
• Few-shot Scene-adaptive Anomaly Detection
• ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
• Structure-Enhanced Meta-Learning For Few-Shot Graph Classification
• MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation
• Learning to Filter: Siamese Relation Network for Robust Tracking
• Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
• Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning
• Prototypical Networks for Multi-Label Learning
• Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning
• Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification
• Multi-Source Domain Adaptation with Mixture of Experts
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• One Shot Learning for Speech Separation
• Train and You'll Miss It: Interactive Model Iteration with Weak Supervision and Pre-Trained Embeddings
• Orthogonal Over-Parameterized Training
• Meta-Learning for Relative Density-Ratio Estimation
• Large-Scale Historical Watermark Recognition: dataset and a new consistency-based approach
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction
• Variational Feature Disentangling for Fine-Grained Few-Shot Classification
• Function Contrastive Learning of Transferable Meta-Representations
• Knowledge Guided Metric Learning for Few-Shot Text Classification
• SketchEmbedNet: Learning Novel Concepts by Imitating Drawings
• Are We Hungry for 3D LiDAR Data for Semantic Segmentation? A Survey and Experimental Study
• Distributed Evolution Strategies Using TPUs for Meta-Learning
• A Study of Few-Shot Audio Classification
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• Faster Optimization-Based Meta-Learning Adaptation Phase
• Learning Compositional Representation for Few-shot Visual Question Answering
• ReMP: Rectified Metric Propagation for Few-Shot Learning
• Compositional Fine-Grained Low-Shot Learning
• An Information-Geometric Distance on the Space of Tasks
• Learning to match transient sound events using attentional similarity for few-shot sound recognition
• Gradual Domain Adaptation via Self-Training of Auxiliary Models
• Self-Supervised Tuning for Few-Shot Segmentation
• Few-shot Conformal Prediction with Auxiliary Tasks
• Exemplar-Based Open-Set Panoptic Segmentation Network
• MANGA: Method Agnostic Neural-policy Generalization and Adaptation
• Few-Shot Learning with Intra-Class Knowledge Transfer
• Resembled Generative Adversarial Networks: Two Domains with Similar Attributes
• SAFCAR: Structured Attention Fusion for Compositional Action Recognition
• Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction
• Learning Image Labels On-the-fly for Training Robust Classification Models
• One-Shot Weakly Supervised Video Object Segmentation
• Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning
• Similarity of Classification Tasks
• Augmented Natural Language for Generative Sequence Labeling
• Physics-aware Spatiotemporal Modules with Auxiliary Tasks for Meta-Learning
• MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition
• Improving Few-Shot Learning with Auxiliary Self-Supervised Pretext Tasks
• Hierarchical Expert Networks for Meta-Learning
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition
• Learning to See Through Obstructions with Layered Decomposition
• Efficient Gradient Approximation Method for Constrained Bilevel Optimization
• Ontology-based n-ball Concept Embeddings Informing Few-shot Image Classification
• Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes
• Joint Image-Instance Spatial-Temporal Attention for Few-shot Action Recognition
• SML: Semantic Meta-learning for Few-shot Semantic Segmentation
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data
• HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical Networks for Low-Resource Headphones
• Discriminative Few-Shot Learning Based on Directional Statistics
• Attentive Feature Reuse for Multi Task Meta learning
• Real-Time Visual Object Tracking via Few-Shot Learning
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• FedSC: Federated Learning with Semantic-Aware Collaboration
• AFD-Net: Adaptive Fully-Dual Network for Few-Shot Object Detection
• Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
• Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
• Solving Large-Scale Extensive-Form Network Security Games via Neural Fictitious Self-Play
• Gradual Relation Network: Decoding Intuitive Upper Extremity Movement Imaginations Based on Few-Shot EEG Learning
• ORBIT: A Real-World Few-Shot Dataset for Teachable Object Recognition
• Hierarchical Protein Function Prediction with Tail-GNNs
• Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains
• Few-Shot Semantic Segmentation Augmented with Image-Level Weak Annotations
• Dialog Intent Induction with Deep Multi-View Clustering
• Are Fewer Labels Possible for Few-shot Learning?
• Lifelong Intent Detection via Multi-Strategy Rebalancing
• Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models
• Variational Metric Scaling for Metric-Based Meta-Learning
• ProtoInfoMax: Prototypical Networks with Mutual Information Maximization for Out-of-Domain Detection
• A Deeper Look at Salient Object Detection: Bi-stream Network with a Small Training Dataset
• Contextualizing Enhances Gradient Based Meta Learning
• CAFENet: Class-Agnostic Few-Shot Edge Detection Network
• Deep Mixed Effect Model using Gaussian Processes: A Personalized and Reliable Prediction for Healthcare
• A Foliated View of Transfer Learning
• Subspace Representation Learning for Few-shot Image Classification
• Improving Few-shot Learning by Spatially-aware Matching and CrossTransformer
• Source-Free Domain Adaptive Fundus Image Segmentation with Denoised Pseudo-Labeling
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation
• Few Is Enough: Task-Augmented Active Meta-Learning for Brain Cell Classification
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding
• Memory-Based Neighbourhood Embedding for Visual Recognition
• Bilevel Optimization for Machine Learning: Algorithm Design and Convergence Analysis
• Decoder Choice Network for Meta-Learning
• Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System
• Task-adaptive Neural Process for User Cold-Start Recommendation
• HetMAML: Task-Heterogeneous Model-Agnostic Meta-Learning for Few-Shot Learning Across Modalities
• Learning-to-Learn Personalised Human Activity Recognition Models
• A Primal-Dual Subgradient Approachfor Fair Meta Learning
• Open Compound Domain Adaptation
• Bidirectional RNN-based Few Shot Learning for 3D Medical Image Segmentation
• Provably Robust Metric Learning
• Alleviating the Incompatibility between Cross Entropy Loss and Episode Training for Few-shot Skin Disease Classification
• Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification
• Temporal Alignment Prediction for Few-Shot Video Classification
• Training Object Detectors from Few Weakly-Labeled and Many Unlabeled Images
• TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation
• Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks
• Single-View 3D Object Reconstruction from Shape Priors in Memory
• Learning to Compare Relation: Semantic Alignment for Few-Shot Learning
• Meta-Learning with Network Pruning
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning Approach
• Learning Continually from Low-shot Data Stream
• Model-Agnostic Meta-Learning for EEG Motor Imagery Decoding in Brain-Computer-Interfacing
• Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning
• Global Semantic Description of Objects based on Prototype Theory
• Deep Metric Learning for Open World Semantic Segmentation
• Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
• Machine Learning Applications for Therapeutic Tasks with Genomics Data
• Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
• Few-Shot Abstract Visual Reasoning With Spectral Features
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
• Data-Efficient Graph Embedding Learning for PCB Component Detection
• Factors for the Generalisation of Identity Relations by Neural Networks
• Distributionally Robust Weighted $k$-Nearest Neighbors
• Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification
• OmniPrint: A Configurable Printed Character Synthesizer
• MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
• 3D Meta-Segmentation Neural Network
• Learn Faster and Forget Slower via Fast and Stable Task Adaptation
• Few-Shot Learning-Based Human Activity Recognition
• An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset
• Composing Neural Learning and Symbolic Reasoning with an Application to Visual Discrimination
• Incremental Meta-Learning via Indirect Discriminant Alignment
• Group Equivariant Conditional Neural Processes
• Transductive Few-Shot Learning: Clustering is All You Need?
• Gaussian Process Meta Few-shot Classifier Learning via Linear Discriminant Laplace Approximation
• Quality Assessment of DIBR-synthesized views: An Overview
• Land Cover Mapping in Limited Labels Scenario: A Survey
• Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
• Few-Shot NLU with Vector Projection Distance and Abstract Triangular CRF
• An end-to-end approach for the verification problem: learning the right distance
• Federated Reconnaissance: Efficient, Distributed, Class-Incremental Learning
• Predicting the Accuracy of a Few-Shot Classifier
• Few Shot Activity Recognition Using Variational Inference
• PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
• Streaming Self-Training via Domain-Agnostic Unlabeled Images
• One-Shot Segmentation in Clutter
• Few-shot Object Detection with Self-adaptive Attention Network for Remote Sensing Images
• Contextual HyperNetworks for Novel Feature Adaptation
• Few-shot Intent Classification and Slot Filling with Retrieved Examples
• Interpretable Time-series Classification on Few-shot Samples
• Hierarchical Meta Learning
• Unsupervised Image Classification for Deep Representation Learning
• Model-Agnostic Graph Regularization for Few-Shot Learning
• DocFace+: ID Document to Selfie Matching
• How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning
• One-Click Annotation with Guided Hierarchical Object Detection
• 3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds
• Introducing the structural bases of typicality effects in deep learning
• AMP0: Species-Specific Prediction of Anti-microbial Peptides using Zero and Few Shot Learning
• Disentangling 3D Prototypical Networks For Few-Shot Concept Learning
• Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning
• Addressing the Real-world Class Imbalance Problem in Dermatology
• Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data
• One-shot Learning for Temporal Knowledge Graphs
• Task-Adaptive Feature Transformer for Few-Shot Segmentation
• A Hybrid Approach with Optimization and Metric-based Meta-Learner for Few-Shot Learning
• On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing
• Theoretical bounds on estimation error for meta-learning
• Few-shot Continual Learning: a Brain-inspired Approach
• Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization
• Out-of-Domain Detection for Low-Resource Text Classification Tasks
• Multi-view Contrastive Learning for Online Knowledge Distillation
• Few-shot Learning for Spatial Regression
• Neural relation extraction: a survey
• Pareto Self-Supervised Training for Few-Shot Learning
• Automating Chapter-Level Classification for Electronic Theses and Dissertations
• Prior-Enhanced Few-Shot Segmentation with Meta-Prototypes
• Shot in the Dark: Few-Shot Learning with No Base-Class Labels
• Uniform Priors for Data-Efficient Transfer
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• Multi-Label Few-Shot Learning for Aspect Category Detection
• AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
• Asymmetric Distribution Measure for Few-shot Learning
• The Disruptions of 5G on Data-driven Technologies and Applications
• Deep Context-Aware Novelty Detection
• Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
• Prototypical quadruplet for few-shot class incremental learning
• Multi-step Estimation for Gradient-based Meta-learning
• Long-term Cross Adversarial Training: A Robust Meta-learning Method for Few-shot Classification Tasks
• Active Transfer Prototypical Network: An Efficient Labeling Algorithm for Time-Series Data
• GCCN: Global Context Convolutional Network
• Categorizing Items with Short and Noisy Descriptions using Ensembled Transferred Embeddings
• A Relational Model for One-Shot Classification
• Inconsistent Few-Shot Relation Classification via Cross-Attentional Prototype Networks with Contrastive Learning
• ConvFiT: Conversational Fine-Tuning of Pretrained Language Models
• Prior Omission of Dissimilar Source Domain(s) for Cost-Effective Few-Shot Learning
• Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining
• 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations
• Learning Class-level Prototypes for Few-shot Learning
• Combining Domain-Specific Meta-Learners in the Parameter Space for Cross-Domain Few-Shot Classification
• TL-SDD: A Transfer Learning-Based Method for Surface Defect Detection with Few Samples
• Few-Sample Named Entity Recognition for Security Vulnerability Reports by Fine-Tuning Pre-Trained Language Models
• Human-In-The-Loop Document Layout Analysis
• Will Multi-modal Data Improves Few-shot Learning?
• Improving the Generalization of Meta-learning on Unseen Domains via Adversarial Shift
• Learning a Discriminant Latent Space with Neural Discriminant Analysis
• Few-shot Learning for Unsupervised Feature Selection
• Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
• Trainable Class Prototypes for Few-Shot Learning
• Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering
• Confusable Learning for Large-class Few-Shot Classification
• One Representation to Rule Them All: Identifying Out-of-Support Examples in Few-shot Learning with Generic Representations
• Personalizing Pre-trained Models
• Adaptive Knowledge-Enhanced Bayesian Meta-Learning for Few-shot Event Detection
• Deep Repulsive Prototypes for Adversarial Robustness
• Learning to Bridge Metric Spaces: Few-shot Joint Learning of Intent Detection and Slot Filling
• Improving Few-shot Learning with Weakly-supervised Object Localization
• System Identification via Meta-Learning in Linear Time-Varying Environments
• Connecting Context-specific Adaptation in Humans to Meta-learning
• Variable-Shot Adaptation for Online Meta-Learning
• Towards Recognizing New Semantic Concepts in New Visual Domains
• Few Shot Learning With No Labels
• Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
• Automatic Face Understanding: Recognizing Families in Photos
• Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning
• AdaVocoder: Adaptive Vocoder for Custom Voice
• Online Meta Adaptation for Variable-Rate Learned Image Compression
• Diversified Multi-prototype Representation for Semi-supervised Segmentation
• A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
• Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining
• Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
• Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
• Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation
• Identifying Physical Law of Hamiltonian Systems via Meta-Learning
• Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
• Enabling the Network to Surf the Internet
• Meta-learning One-class Classifiers with Eigenvalue Solvers for Supervised Anomaly Detection
• Memory Efficient Meta-Learning with Large Images
• Few-shot Learning with Global Relatedness Decoupled-Distillation
• Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
• Zero-Shot Controlled Generation with Encoder-Decoder Transformers
• Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data
• Learning Implicit Temporal Alignment for Few-shot Video Classification
• End-to-end One-shot Human Parsing
• Updatable Siamese Tracker with Two-stage One-shot Learning
• Progressive Cluster Purification for Transductive Few-shot Learning
• Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspection
• Federated Few-Shot Learning with Adversarial Learning
• Mini-Batch Consistent Slot Set Encoder for Scalable Set Encoding
• Modular Adaptation for Cross-Domain Few-Shot Learning
• Explainability-aided Domain Generalization for Image Classification
• Large-Scale Meta-Learning with Continual Trajectory Shifting
• Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution
• Supervised Momentum Contrastive Learning for Few-Shot Classification
• Robustness of Meta Matrix Factorization Against Strict Privacy Constraints
• Extended Few-Shot Learning: Exploiting Existing Resources for Novel Tasks
• Few-Shot Event Detection with Prototypical Amortized Conditional Random Field
• Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes
• Annotation-Efficient Untrimmed Video Action Recognition
• Momentum Contrast Speaker Representation Learning
• Learning to Decouple Relations: Few-Shot Relation Classification with Entity-Guided Attention and Confusion-Aware Training
• Deep Low-Shot Learning for Biological Image Classification and Visualization from Limited Training Samples
• Why Do Better Loss Functions Lead to Less Transferable Features?
• Few-shot learning via tensor hallucination
• Uncertainty-Aware Few-Shot Image Classification
• Challenges in Vessel Behavior and Anomaly Detection: From Classical Machine Learning to Deep Learning
• Empirical Perspectives on One-Shot Semi-supervised Learning
• AlphaNet: Improving Long-Tail Classification By Combining Classifiers
• Learning to Profile: User Meta-Profile Network for Few-Shot Learning
• Generalized Few-Shot Video Classification with Video Retrieval and Feature Generation
• Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network
• Memory-Augmented Relation Network for Few-Shot Learning
• Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
• LFD-ProtoNet: Prototypical Network Based on Local Fisher Discriminant Analysis for Few-shot Learning
• Towards Robust Pattern Recognition: A Review
• Proximal Mapping for Deep Regularization
• Few-shot 3D Point Cloud Semantic Segmentation
• Discrete Few-Shot Learning for Pan Privacy
• Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering
• One-Shot Domain Adaptation For Face Generation
• Semi-supervised Learning with a Teacher-student Network for Generalized Attribute Prediction
• An Artificial Intelligence-Based System to Assess Nutrient Intake for Hospitalised Patients
• Task-Adaptive Clustering for Semi-Supervised Few-Shot Classification
• Bias-Awareness for Zero-Shot Learning the Seen and Unseen
• Fine-grained Image-to-Image Transformation towards Visual Recognition
• No Representation without Transformation
• Webly Supervised Image Classification with Self-Contained Confidence
• Adversarial Dual Distinct Classifiers for Unsupervised Domain Adaptation
• Few-Shot Object Detection via Knowledge Transfer
• Knowledge Efficient Deep Learning for Natural Language Processing
• Meta Matrix Factorization for Federated Rating Predictions
• Graph convolutional networks for learning with few clean and many noisy labels
• DECoVaC: Design of Experiments with Controlled Variability Components
• A New Few-shot Segmentation Network Based on Class Representation
• BEAN: Interpretable Representation Learning with Biologically-Enhanced Artificial Neuronal Assembly Regularization
• Domain-Agnostic Few-Shot Classification by Learning Disparate Modulators
• Adaptive Text Recognition through Visual Matching
• Using Sensory Time-cue to enable Unsupervised Multimodal Meta-learning
• TGG: Transferable Graph Generation for Zero-shot and Few-shot Learning
• Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learning
• MAME : Model-Agnostic Meta-Exploration
• An Approach for Adaptive Automatic Threat Recognition Within 3D Computed Tomography Images for Baggage Security Screening
• Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts
• DeepConsensus: using the consensus of features from multiple layers to attain robust image classification
• Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax
• Multi-level Similarity Learning for Low-Shot Recognition
• Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance
• Representation based and Attention augmented Meta learning
• Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
• Local Nonparametric Meta-Learning
• CRL: Class Representative Learning for Image Classification
• Open-Ended Content-Style Recombination Via Leakage Filtering
• Distribution Networks for Open Set Learning
• Low-Shot Learning from Imaginary 3D Model
• Continual Learning Augmented Investment Decisions
• Contextual Memory Trees
• Meta-Learner with Linear Nulling
• f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
• A Content-Based Approach to Email Triage Action Prediction: Exploration and Evaluation
• Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks
• End-to-End Learning of Deep Kernel Acquisition Functions for Bayesian Optimization
• Meta Cross-Modal Hashing on Long-Tailed Data
• Unifying Few- and Zero-Shot Egocentric Action Recognition
• A Review of Computer Vision Methods in Network Security
• One-Shot Image Classification by Learning to Restore Prototypes
• Augmented Bi-path Network for Few-shot Learning
• Generalized Reinforcement Meta Learning for Few-Shot Optimization
• Learning to Learn Image Classifiers with Visual Analogy
• Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning
• Honey or Poison? Solving the Trigger Curse in Few-shot Event Detection via Causal Intervention
• Few-shot Learning with LSSVM Base Learner and Transductive Modules
• Relation-aware Meta-learning for Market Segment Demand Prediction with Limited Records
• Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning
• Dataset Bias in Few-shot Image Recognition
• Efficient Deep Representation Learning by Adaptive Latent Space Sampling
• One-Class Meta-Learning: Towards Generalizable Few-Shot Open-Set Classification
• Training few-shot classification via the perspective of minibatch and pretraining
• MA 3 : Model Agnostic Adversarial Augmentation for Few Shot learning
• Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers
• Learning Mixtures of Low-Rank Models
• Optimization of Image Embeddings for Few Shot Learning
• Aerial Scene Understanding in The Wild: Multi-Scene Recognition via Prototype-based Memory Networks
• Few-shot Learning for Topic Modeling
• Characterizing Policy Divergence for Personalized Meta-Reinforcement Learning
• MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization
• Meta-Active Learning for Node Response Prediction in Graphs
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation
• Learning Clusterable Visual Features for Zero-Shot Recognition
• Do We Really Need Gold Samples for Sample Weighting Under Label Noise?
• Learning by Examples Based on Multi-level Optimization
• Representation Learning from Limited Educational Data with Crowdsourced Labels
• Leveraging External Knowledge for Out-Of-Vocabulary Entity Labeling
• Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition
• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
• Fair Meta-Learning For Few-Shot Classification
• Unfairness Discovery and Prevention For Few-Shot Regression
• OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
• Learning to Generate Task-Specific Adapters from Task Description
• Reinforced Attention for Few-Shot Learning and Beyond
• Prototypical Region Proposal Networks for Few-Shot Localization and Classification
• Attribute-Based Robotic Grasping with One-Grasp Adaptation
• Few-Shot Meta-Denoising
• BOML: A Modularized Bilevel Optimization Library in Python for Meta Learning
• Hyperspherical embedding for novel class classification
• Extracting the Unknown from Long Math Problems
• Towards Enabling Meta-Learning from Target Models
• Opening up Open-World Tracking
• Few-Shot Video Object Detection
• Non-Parametric Few-Shot Learning for Word Sense Disambiguation
• Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition
• Pseudo Siamese Network for Few-shot Intent Generation
• OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation
• Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving
• Learning from Web Data with Self-Organizing Memory Module
• Ensemble Making Few-Shot Learning Stronger
• Probabilistic task modelling for meta-learning
• Geo-Spatiotemporal Features and Shape-Based Prior Knowledge for Fine-grained Imbalanced Data Classification
• Tackling Long-Tailed Relations and Uncommon Entities in Knowledge Graph Completion
• CLTA: Contents and Length-based Temporal Attention for Few-shot Action Recognition
• Task Attended Meta-Learning for Few-Shot Learning
• Finding Significant Features for Few-Shot Learning using Dimensionality Reduction
• Metric Learning with Background Noise Class for Few-shot Detection of Rare Sound Events
• Multi-Pretext Attention Network for Few-shot Learning with Self-supervision
• Uniform Sampling over Episode Difficulty
• Unsupervised Local Discrimination for Medical Images
• Online Unsupervised Learning of Visual Representations and Categories
• Low-Resource Named Entity Recognition Based on Multi-hop Dependency Trigger
• Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce
• Meta Learning Low Rank Covariance Factors for Energy-Based Deterministic Uncertainty
• Local Contrast Learning
• ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI
• Meta-Learning with Adjoint Methods
• TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary Data
• Meta-learning on Spectral Images of Electroencephalogram of Schizophenics
• Attention Guided Cosine Margin For Overcoming Class-Imbalance in Few-Shot Road Object Detection
• Meta-Forecasting by combining Global Deep Representations with Local Adaptation
• Generating meta-learning tasks to evolve parametric loss for classification learning
• One-shot Weakly-Supervised Segmentation in Medical Images
• Metric Learning for Dynamic Text Classification
• An Explicit-Joint and Supervised-Contrastive Learning Framework for Few-Shot Intent Classification and Slot Filling
• Adaptive Transfer Learning: a simple but effective transfer learning
• Revisiting Self-Training for Few-Shot Learning of Language Model
• Coarse-To-Fine Incremental Few-Shot Learning
• Privacy-Preserving Serverless Edge Learning with Decentralized Small Data
• Inductive Granger Causal Modeling for Multivariate Time Series
• Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
• Meta-Learning for Koopman Spectral Analysis with Short Time-series
• Few-shot time series segmentation using prototype-defined infinite hidden Markov models
• Challenging Images For Minds and Machines
• Condensed Composite Memory Continual Learning
• Crowdsourcing with Meta-Workers: A New Way to Save the Budget
• Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning
• Few-shot Image Classification with Multi-Facet Prototypes
• On Data Efficiency of Meta-learning
• Few-Shot Semantic Parsing for New Predicates
• BED: Bi-Encoder-Based Detectors for Out-of-Distribution Detection
• Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited Communication
• End-to-End Refinement Guided by Pre-trained Prototypical Classifier
• Few-Shot Learning: Expanding ID Cards Presentation Attack Detection to Unknown ID Countries
• Leveraging Semantic Embeddings for Safety-Critical Applications
• MENTOR: Multilingual tExt detectioN TOward leaRning by analogy
• Exploring Task Difficulty for Few-Shot Relation Extraction
• Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
• Supervised attention for speaker recognition
• Music Rearrangement Using Hierarchical Segmentation
• Margin-Based Transfer Bounds for Meta Learning with Deep Feature Embedding
• Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation
• MDFM: Multi-Decision Fusing Model for Few-Shot Learning
• Prototype Matching Networks for Large-Scale Multi-label Genomic Sequence Classification
• Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning
• Adaptive Submodular Meta-Learning
• Meta learning to classify intent and slot labels with noisy few shot examples
• HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression
• Who calls the shots? Rethinking Few-Shot Learning for Audio
• PCPs: Patient Cardiac Prototypes
• BiOpt: Bi-Level Optimization for Few-Shot Segmentation
• Power Normalizing Second-order Similarity Network for Few-shot Learning
• Semi-Supervised Few-Shot Classification with Deep Invertible Hybrid Models
• Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images
• Diversity Transfer Network for Few-Shot Learning
• On Hard Episodes in Meta-Learning
• TexRel: a Green Family of Datasets for Emergent Communications on Relations
• Conditional Deep Convolutional Neural Networks for Improving the Automated Screening of Histopathological Images
• Stochastic Whitening Batch Normalization
• Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation
• Meta-learning for downstream aware and agnostic pretraining
• RSG: A Simple but Effective Module for Learning Imbalanced Datasets
• Mutual-Information Based Few-Shot Classification
• One-Shot Affordance Detection
• Meta-learning for Matrix Factorization without Shared Rows or Columns
• IoT Network Behavioral Fingerprint Inference with Limited Network Trace for Cyber Investigation: A Meta Learning Approach
• Exploiting a Zoo of Checkpoints for Unseen Tasks
• A Transductive Maximum Margin Classifier for Few-Shot Learning
• GRCN: Graph-Refined Convolutional Network for Multimedia Recommendation with Implicit Feedback
• DAMSL: Domain Agnostic Meta Score-based Learning
• Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes
• Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP
• Zero-Shot Compositional Concept Learning
• Are You Sure You Want To Do That? Classification with Verification
• Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning
• Few-shot acoustic event detection via meta-learning
• Novelty-Prepared Few-Shot Classification
• Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error
• Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision
• Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning
• CLARA: Clinical Report Auto-completion
• Composing Text and Image for Image Retrieval - An Empirical Odyssey
• External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery
• Learning to Transfer: A Foliated Theory
• Boosting Few-Shot Classification with View-Learnable Contrastive Learning
• MetaMIML: Meta Multi-Instance Multi-Label Learning
• CvS: Classification via Segmentation For Small Datasets
• Meta Guided Metric Learner for Overcoming Class Confusion in Few-Shot Road Object Detection
• Domain invariant hierarchical embedding for grocery products recognition
• Dual-Tuning: Joint Prototype Transfer and Structure Regularization for Compatible Feature Learning
• Cooperative Bi-path Metric for Few-shot Learning
• One-Shot Object Affordance Detection in the Wild
• The Sample Complexity of Meta Sparse Regression
• Meta Self-Learning for Multi-Source Domain Adaptation: A Benchmark
• When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
• Improving Sample Efficiency with Normalized RBF Kernels
• Adaptation-Agnostic Meta-Training
• Designing Neural Speaker Embeddings with Meta Learning
• Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
• One-Shot Learning for Language Modelling
• Realizing Continual Learning through Modeling a Learning System as a Fiber Bundle
• Context-Transformer: Tackling Object Confusion for Few-Shot Detection
• Decoupling Features and Coordinates for Few-shot RGB Relocalization
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition
• Learning to Generalize to Unseen Tasks with Bilevel Optimization
• Exploit Clues from Views: Self-Supervised and Regularized Learning for Multiview Object Recognition
• Unlocking the Full Potential of Small Data with Diverse Supervision
• Nearest Neighbour Few-Shot Learning for Cross-lingual Classification
• Accelerating Gradient-based Meta Learner
• Unique Chinese Linguistic Phenomena
• Meta Learning in the Continuous Time Limit
• A Few-Shot Sequential Approach for Object Counting
• Adaptive additive classification-based loss for deep metric learning
• Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis
• OvA-INN: Continual Learning with Invertible Neural Networks
• One of these (Few) Things is Not Like the Others
• Don't Wait, Just Weight: Improving Unsupervised Representations by Learning Goal-Driven Instance Weights
• Class Interference Regularization
• MapRE: An Effective Semantic Mapping Approach for Low-resource Relation Extraction
• Channel Relationship Prediction with Forget-Update Module for Few-shot Classification
• Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
• One-shot Text Field Labeling using Attention and Belief Propagation for Structure Information Extraction
• Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data
• Covariate Distribution Aware Meta-learning
• Submodular Meta-Learning
• Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
• Self-Denoising Neural Networks for Few Shot Learning
• Proxy Network for Few Shot Learning