mlsanityData to 14 Oct 2026

Task-Oriented Channel Attention for Fine-Grained Few-Shot Classification

arXiv 2308.00093 ↗First posted 28 Jul 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

The difficulty of the fine-grained image classification mainly comes from a shared overall appearance across classes. Thus, recognizing discriminative details, such as eyes and beaks for birds, is a key in the task. However, this is particularly challenging when training data is limited. To address this, we propose Task Discrepancy Maximization (TDM), a task-oriented channel attention method tailored for fine-grained few-shot classification with two novel modules Support Attention Module (SAM) and Query Attention Module (QAM). SAM highlights channels encoding class-wise discriminative features, while QAM assigns higher weights to object-relevant channels of the query. Based on these submodules, TDM produces task-adaptive features by focusing on channels encoding class-discriminative details and possessed by the query at the same time, for accurate class-sensitive similarity measure between support and query instances. While TDM influences high-level feature maps by task-adaptive calibration of channel-wise importance, we further introduce Instance Attention Module (IAM) operating in intermediate layers of feature extractors to instance-wisely highlight object-relevant channels, by extending QAM. The merits of TDM and IAM and their complementary benefits are experimentally validated in fine-grained few-shot classification tasks. Moreover, IAM is also shown to be effective in coarse-grained and cross-domain few-shot classifications.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 55 of its 78 references that are in the map. First posted on arXiv 28 Jul 2023.

Builds on

55 of 78 references.

References · 55

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  5. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  6. 2017Squeeze-and-Excitation Networkscited by 4,789
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2018CBAM: Convolutional Block Attention Modulecited by 2,477
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2013Fine-Grained Visual Classification of Aircraftcited by 1,726
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
38 more
  1. 2019A Closer Look at Few-shot Classificationcited by 684
  2. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  3. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  4. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  5. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  6. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  7. 2017A Structured Self-attentive Sentence Embeddingcited by 318
  8. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  9. 2019Hyperbolic Image Embeddingscited by 221
  10. 2019Cross Attention Network for Few-shot Classificationcited by 219
  11. 2023DepGraph: Towards Any Structural Pruningcited by 203
  12. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  13. 2020Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learningcited by 179
  14. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  15. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
  16. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  17. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  18. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  19. 2019Edge-labeling Graph Neural Network for Few-shot Learningcited by 114
  20. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  21. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  22. 2019Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-grained Image Recognitioncited by 95
  23. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  24. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  25. 2021Relational Embedding for Few-Shot Classificationcited by 74
  26. 2019Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Upcited by 66
  27. 2019Associative Alignment for Few-shot Image Classificationcited by 58
  28. 2020Spatial Attention Pyramid Network for Unsupervised Domain Adaptationcited by 56
  29. 2021Pareto Self-Supervised Training for Few-Shot Learningcited by 52
  30. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
  31. 2022Joint Distribution Matters: Deep Brownian Distance Covariance for Few-Shot Classificationcited by 50
  32. 2021Learning Dynamic Alignment via Meta-filter for Few-shot Learningcited by 41
  33. 2023Leveraging Hidden Positives for Unsupervised Semantic Segmentationcited by 40
  34. 2022Rethinking Generalization in Few-Shot Classificationcited by 36
  35. 2019Few-Shot Learning with Localization in Realistic Settingscited by 34
  36. 2020Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learningcited by 31
  37. 2022Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learningcited by 27
  38. 2015Diversity Networks: Neural Network Compression Using Determinantal Point Processescited by 25

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2026Adaptive receptive field-based spatial-frequency feature reconstruction network for fine-grained few-shot image classificationcited by 2
  2. 2025Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classificationcited by 0
  3. 2025Color as the Impetus: Transforming Few-Shot Learnercited by 0
  4. 2026Phase-Aware Spatial-Frequency Fusion for Few-Shot Fine-Grained Image Classificationcited by 0