mlsanityData to 7 Oct 2026

Reinforced Attention for Few-Shot Learning and Beyond

arXiv 2104.04192 ↗First posted 9 Apr 2021cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Few-shot learning aims to correctly recognize query samples from unseen classes given a limited number of support samples, often by relying on global embeddings of images. In this paper, we propose to equip the backbone network with an attention agent, which is trained by reinforcement learning. The policy gradient algorithm is employed to train the agent towards adaptively localizing the representative regions on feature maps over time. We further design a reward function based on the prediction of the held-out data, thus helping the attention mechanism to generalize better across the unseen classes. The extensive experiments show, with the help of the reinforced attention, that our embedding network has the capability to progressively generate a more discriminative representation in few-shot learning. Moreover, experiments on the task of image classification also show the effectiveness of the proposed design.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 43 of its 71 references that are in the map. First posted on arXiv 9 Apr 2021.

Builds on

43 of 71 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Densely Connected Convolutional Networkscited by 6,691
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2017Squeeze-and-Excitation Networkscited by 4,763
  8. 2015Continuous control with deep reinforcement learningcited by 3,279
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2018CBAM: Convolutional Block Attention Modulecited by 2,463
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2016Matching Networks for One Shot Learningcited by 2,246
31 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  2. 2019A Closer Look at Few-shot Classificationcited by 679
  3. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  4. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  5. 2014Recurrent Models of Visual Attentioncited by 344
  6. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 304
  7. 2019Hyperbolic Image Embeddingscited by 219
  8. 2019Cross Attention Network for Few-shot Classificationcited by 218
  9. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  10. 2019Few-Shot Object Detection with Attention-RPN and Multi-Relation Detectorcited by 206
  11. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  12. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  13. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  14. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  15. 2015End-to-end Learning of Action Detection from Frame Glimpses in Videoscited by 101
  16. 2020Laplacian Regularized Few-Shot Learningcited by 90
  17. 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
  18. 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
  19. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  20. 2018Incremental Few-Shot Learning with Attention Attractor Networkscited by 65
  21. 2015Active Object Localization with Deep Reinforcement Learningcited by 42
  22. 2018Few-Shot Learning with Metric-Agnostic Conditional Embeddingscited by 40
  23. 2018Variance Reduction for Reinforcement Learning in Input-Driven Environmentscited by 30
  24. 2019Learning an Adaptive Learning Rate Schedulecited by 29
  25. 2019Towards Robust Image Classification Using Sequential Attention Modelscited by 27
  26. 2021PFRL: Pose-Free Reinforcement Learning for 6D Pose Estimationcited by 14
  27. 2018How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarizationcited by 13
  28. 2016PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learningcited by 9
  29. 2020Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classificationcited by 7
  30. 2019Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigationcited by 6
  31. 2019Actor-Critic Instance Segmentationcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 6; 2023: 5; 2024: 0; 2025: 1.

18 papers.

Sort:

  1. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  2. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  3. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  4. 2021Meta-Learning for Multi-Label Few-Shot Classificationcited by 21
  5. 2022Task Discrepancy Maximization for Fine-grained Few-Shot Classificationcited by 21
  6. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  7. 2025Reliable Few-shot Learning under Dual Noisescited by 16
  8. 2021Adaptive Poincar'e Point to Set Distance for Few-Shot Classificationcited by 15
  9. 2023DETA: Denoised Task Adaptation for Few-Shot Learningcited by 13
  10. 2022CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classificationcited by 9
  11. 2021Prototype Completion for Few-Shot Learningcited by 7
  12. 2022RankDNN: Learning to Rank for Few-shot Learningcited by 7
6 more
  1. 2021Adaptive Feature Interpolation for Low-Shot Image Generationcited by 6
  2. 2023Task-Oriented Channel Attention for Fine-Grained Few-Shot Classificationcited by 4
  3. 2022Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspectivecited by 3
  4. 2021Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learningcited by 1
  5. 2023Task Adaptive Feature Transformation for One-Shot Learningcited by 1
  6. 2023Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learningcited by 0