mlsanityData to 14 Oct 2026

Rectifying the Shortcut Learning of Background for Few-Shot Learning

arXiv 2107.07746 ↗First posted 16 Jul 2021cs.CVcited by 51

Not on the map. Why?

Abstract (arXiv)

The category gap between training and evaluation has been characterised as one of the main obstacles to the success of Few-Shot Learning (FSL). In this paper, we for the first time empirically identify image background, common in realistic images, as a shortcut knowledge helpful for in-class classification but ungeneralizable beyond training categories in FSL. A novel framework, COSOC, is designed to tackle this problem by extracting foreground objects in images at both training and evaluation without any extra supervision. Extensive experiments carried on inductive FSL tasks demonstrate the effectiveness of our approaches.

Key facts. Cited by 51 papers in the map (data through 14 Oct 2026). Builds on 48 of its 74 references that are in the map. First posted on arXiv 16 Jul 2021.

Builds on

48 of 74 references.

References · 48

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2016Matching Networks for One Shot Learningcited by 2,255
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,432
  11. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  12. 2020Meta-Learning in Neural Networks: A Surveycited by 950
36 more
  1. 2019A Closer Look at Few-shot Classificationcited by 684
  2. 2018Recognition in Terra Incognitacited by 658
  3. 2019Meta-Learning with Implicit Gradientscited by 525
  4. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  5. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  6. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  7. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  8. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  9. 2017Meta-SGD: Learning to Learn Quickly for Few-Shot Learningcited by 379
  10. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 343
  11. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  12. 2017Meta Networkscited by 269
  13. 2019Cross Attention Network for Few-shot Classificationcited by 219
  14. 2018Low-Shot Learning from Imaginary Datacited by 181
  15. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  16. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  17. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  18. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  19. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  20. 2020Interventional Few-Shot Learningcited by 112
  21. 2020What makes instance discrimination good for transfer learning?cited by 111
  22. 2020Adversarial Feature Hallucination Networks for Few-Shot Learningcited by 110
  23. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  24. 2019TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learningcited by 91
  25. 2018Delta-encoder: an effective sample synthesis method for few-shot object recognitioncited by 89
  26. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  27. 2020Meta-Learning with Adaptive Hyperparameterscited by 79
  28. 2019Meta-Curvaturecited by 70
  29. 2019Associative Alignment for Few-shot Image Classificationcited by 58
  30. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  31. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  32. 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learningcited by 56
  33. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  34. 2019MetaFun: Meta-Learning with Iterative Functional Updatescited by 34
  35. 2020Spatial Contrastive Learning for Few-Shot Classificationcited by 17
  36. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 20; 2023: 14; 2024: 9; 2025: 7; 2026: 1.

51 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  2. 2023A Closer Look at Few-shot Classification Againcited by 46
  3. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  4. 2025Shortcut Learning in Generalist Robot Policies: The Role of Dataset Diversity and Fragmentationcited by 31
  5. 2022How Robust is Unsupervised Representation Learning to Distribution Shift?cited by 24
  6. 2022Self-Promoted Supervision for Few-Shot Transformercited by 22
  7. 2022Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learningcited by 20
  8. 2022Channel Importance Matters in Few-Shot Image Classificationcited by 20
  9. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20
  10. 2025Reliable Few-shot Learning under Dual Noisescited by 17
  11. 2022EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredientscited by 16
  12. 2023Exploring Efficient Few-shot Adaptation for Vision Transformerscited by 16
38 more
  1. 2022Rectify ViT Shortcut Learning by Visual Saliencycited by 14
  2. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  3. 2022Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learningcited by 10
  4. 2022Adaptive Dimension Reduction and Variational Inference for Transductive Few-Shot Classificationcited by 10
  5. 2022An Embarrassingly Simple Approach to Semi-Supervised Few-Shot Learningcited by 10
  6. 2023Masking Strategies for Background Bias Removal in Computer Vision Modelscited by 9
  7. 2022Learning Dense Object Descriptors from Multiple Views for Low-shot Category Generalizationcited by 6
  8. 2023Instance-based Max-margin for Practical Few-shot Recognitioncited by 6
  9. 2023Mitigating the Effect of Incidental Correlations on Part-based Learningcited by 6
  10. 2024Rethinking Visual Content Refinement in Low-Shot CLIP Adaptationcited by 5
  11. 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Modelscited by 5
  12. 2022Revisiting Few-Shot Learning from a Causal Perspectivecited by 4
  13. 2023Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNscited by 4
  14. 2023Clustered-patch Element Connection for Few-shot Learningcited by 4
  15. 2025Preventing Shortcuts in Adapter Training via Providing the Shortcutscited by 4
  16. 2022Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspectivecited by 3
  17. 2023PrototypeFormer: Learning to Explore Prototype Relationships for Few-shot Image Classificationcited by 3
  18. 2024Robust Few-Shot Ensemble Learning with Focal Diversity-Based Pruningcited by 3
  19. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  20. 2024Clean-image Backdoor Attackscited by 2
  21. 2025Free Lunch to Meet the Gap: Intermediate Domain Reconstruction for Cross-Domain Few-Shot Learningcited by 2
  22. 2026Seeing Isn't Always Believing: Analysis of Grad-CAM Faithfulness and Localization Reliability in Lung Cancer CT Classificationcited by 2
  23. 2022Semantically Proportional Patchmix for Few-Shot Learningcited by 1
  24. 2022Fusion-based Few-Shot Morphing Attack Detection and Fingerprintingcited by 1
  25. 2024Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applicationscited by 1
  26. 2024Intra-task Mutual Attention based Vision Transformer for Few-Shot Learningcited by 1
  27. 2024Class-relevant Patch Embedding Selection for Few-Shot Image Classificationcited by 1
  28. 2024Tiny models from tiny data: Textual and null-text inversion for few-shot distillationcited by 1
  29. 2022Semantic Cross Attention for Few-shot Learningcited by 0
  30. 2022A Maximum Log-Likelihood Method for Imbalanced Few-Shot Learning Taskscited by 0
  31. 2023Disambiguation of One-Shot Visual Classification Tasks: A Simplex-Based Approachcited by 0
  32. 2023Gestalt-Guided Image Understanding for Few-Shot Learningcited by 0
  33. 2023Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Workcited by 0
  34. 2023Extreme Image Transformations Facilitate Robust Latent Object Representationscited by 0
  35. 2023Concept-wise Fine-tuning Matters in Preventing Negative Transfercited by 0
  36. 2024GTA: Guided Transfer of Spatial Attention from Object-Centric Representationscited by 0
  37. 2024Siamese Transformer Networks for Few-shot Image Classificationcited by 0
  38. 2025Brain Inspired Adaptive Memory Dual-Net for Few-Shot Image Classificationcited by 0

50 most cited of 51 All 51 (JSON)