mlsanityData to 7 Oct 2026

Boosting Few-Shot Learning via Attentive Feature Regularization

arXiv 2403.17025 ↗First posted 23 Mar 2024cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing operation weakens the feature representation due to the linear interpolation and the overlooking of the importance of specific channels. To solve these issues, this paper proposes attentive feature regularization (AFR) which aims to improve the feature representativeness and discriminability. In our approach, we first calculate the relations between different categories of semantic labels to pick out the related features used for regularization. Then, we design two attention-based calculations at both the instance and channel levels. These calculations enable the regularization procedure to focus on two crucial aspects: the feature complementarity through adaptive interpolation in related categories and the emphasis on specific feature channels. Finally, we combine these regularization strategies to significantly improve the classifier performance. Empirical studies on several popular FSL benchmarks demonstrate the effectiveness of AFR, which improves the recognition accuracy of novel categories without the need to retrain any feature extractor, especially in the 1-shot setting. Furthermore, the proposed AFR can seamlessly integrate into other FSL methods to improve classification performance.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 23 Mar 2024.

Builds on

29 of 51 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2013Describing Textures in the Wildcited by 2,110
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  12. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
17 more
  1. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  2. 2019Cross Attention Network for Few-shot Classificationcited by 218
  3. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  4. 2018Low-Shot Learning from Imaginary Datacited by 181
  5. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  6. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  7. 2018MixUp as Locally Linear Out-Of-Manifold Regularizationcited by 158
  8. 2020Remix: Rebalanced Mixupcited by 144
  9. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  10. 2020Interventional Few-Shot Learningcited by 112
  11. 2023Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinementcited by 84
  12. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  13. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  14. 2021Relational Embedding for Few-Shot Classificationcited by 74
  15. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  16. 2021Binocular Mutual Learning for Improving Few-shot Classificationcited by 26
  17. 2022Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroidcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 3.

10 papers.

  1. 2025On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectificationcited by 121
  2. 2025d2Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Cachingcited by 24
  3. 2025Accelerating Diffusion Transformer via Error-Optimized Cachecited by 14
  4. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  5. 2026Look Carefully: Adaptive Visual Reinforcements in Multimodal Large Language Models for Hallucination Mitigationcited by 7
  6. 2025ACE: Concept Editing in Diffusion Models without Performance Degradationcited by 6
  7. 2025Generalizable Vision-Language Few-Shot Adaptation with Predictive Prompts and Negative Learningcited by 1
  8. 2025Unbiased Max-Min Embedding Classification for Transductive Few-Shot Learning: Clustering and Classification Are All You Needcited by 0
  9. 2026ReCCur: A Recursive Corner-Case Curation Framework for Robust Vision-Language Understanding in Open and Edge Scenarioscited by 0
  10. 2026IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learningcited by 0