Data to 7 Oct 2026

A Closer Look at Few-shot Classification

arXiv 1904.04232 ↗First posted 8 Apr 2019cs.CVcited by 679

Not on the map. Why?

Abstract (arXiv)

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and differences in implementation details make a fair comparison difficult. In this paper, we present 1) a consistent comparative analysis of several representative few-shot classification algorithms, with results showing that deeper backbones significantly reduce the performance differences among methods on datasets with limited domain differences, 2) a modified baseline method that surprisingly achieves competitive performance when compared with the state-of-the-art on both the miniI and the CUB datasets, and 3) a new experimental setting for evaluating the cross-domain generalization ability for few-shot classification algorithms. Our results reveal that reducing intra-class variation is an important factor when the feature backbone is shallow, but not as critical when using deeper backbones. In a realistic cross-domain evaluation setting, we show that a baseline method with a standard fine-tuning practice compares favorably against other state-of-the-art few-shot learning algorithms.

Key facts. Cited by 679 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 193; 2022: 169; 2023: 142; 2024: 92; 2025: 51; 2026: 32.

679 papers.

Sort:

By area:

2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
2021FedBABU: Towards Enhanced Representation for Federated Image Classificationcited by 180
2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
2022Dataset Pruning: Reducing Training Data by Examining Generalization Influencecited by 132
2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
2022Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Differencecited by 123
2021Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Biascited by 115

38 more

2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
2022Self-Support Few-Shot Semantic Segmentationcited by 96
2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
2022Learning from Few Examples: A Summary of Approaches to Few-Shot Learningcited by 86
2021On Learning the Geodesic Path for Incremental Learningcited by 85
2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
2021Crossover Learning for Fast Online Video Instance Segmentationcited by 83
2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
2024Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learningcited by 79
2021Defect-GAN: High-Fidelity Defect Synthesis for Automated Defect Inspectioncited by 77
2022Variational Model Inversion Attackscited by 75
2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
2021Domain Adaptation for Time Series Forecasting via Attention Sharingcited by 68
2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
2023Advances and Challenges in Meta-Learning: A Technical Reviewcited by 65
2021Cross-Domain Few-Shot Classification via Adversarial Task Augmentationcited by 63
2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 63
2021Learning a Universal Template for Few-shot Dataset Generalizationcited by 61
2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
2021Learning to Synthesize Programs as Interpretable and Generalizable Policiescited by 59
2022Transferability in Deep Learning: A Surveycited by 57
2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
2021Universal Representation Learning from Multiple Domains for Few-shot Classificationcited by 56
2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
2021Rectifying the Shortcut Learning of Background for Few-Shot Learningcited by 51
2021Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencodercited by 51
2021StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrievalcited by 50
2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
2021Incremental Few-Shot Instance Segmentationcited by 49
2021Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Datacited by 49
2021Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learningcited by 49
2021Shallow Bayesian Meta Learning for Real-World Few-Shot Recognitioncited by 48
2021Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Datacited by 48
2021StyleAlign: Analysis and Applications of Aligned StyleGAN Modelscited by 48
2021Improving Transferability of Representations via Augmentation-Aware Self-Supervisioncited by 48
2022Meta-DETR: Image-Level Few-Shot Detection with Inter-Class Correlation Exploitationcited by 48
2023STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tablescited by 48

50 most cited of 679 All 679 (JSON)