mlsanityData to 7 Oct 2026

Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-identification

arXiv 2108.08728 ↗First posted 19 Aug 2021cs.CV cs.AI cs.LGcited by 114

Not on the map. Why?

Abstract (arXiv)

Attention mechanism has demonstrated great potential in fine-grained visual recognition tasks. In this paper, we present a counterfactual attention learning method to learn more effective attention based on causal inference. Unlike most existing methods that learn visual attention based on conventional likelihood, we propose to learn the attention with counterfactual causality, which provides a tool to measure the attention quality and a powerful supervisory signal to guide the learning process. Specifically, we analyze the effect of the learned visual attention on network prediction through counterfactual intervention and maximize the effect to encourage the network to learn more useful attention for fine-grained image recognition. Empirically, we evaluate our method on a wide range of fine-grained recognition tasks where attention plays a crucial role, including fine-grained image categorization, person re-identification, and vehicle re-identification. The consistent improvement on all benchmarks demonstrates the effectiveness of our method. Code is available at https://github.com/raoyongming/CAL

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). Builds on 44 of its 70 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

44 of 70 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  3. 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
  4. 2017Counterfactual Fairnesscited by 802
  5. 2016Performance Measures and a Data Set for Multi-Target, Multi-Camera Trackingcited by 685
  6. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  7. 2017Person Transfer GAN to Bridge Domain Gap for Person Re-Identificationcited by 479
  8. 2017Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)cited by 472
  9. 2020Circle Loss: A Unified Perspective of Pair Similarity Optimizationcited by 402
  10. 2017Residual Attention Network for Image Classificationcited by 385
  11. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  12. 2014Recurrent Models of Visual Attentioncited by 344
32 more
  1. 2017Relation Networks for Object Detectioncited by 305
  2. 2019Omni-Scale Feature Learning for Person Re-Identificationcited by 292
  3. 2018Learning Discriminative Features with Multiple Granularities for Person Re-Identificationcited by 290
  4. 2016Hierarchical Question-Image Co-Attention for Visual Question Answeringcited by 278
  5. 2013Direct and Indirect Effectscited by 276
  6. 2018Harmonious Attention Network for Person Re-Identificationcited by 211
  7. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  8. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
  9. 2020Visual Commonsense R-CNNcited by 106
  10. 2018Learning to Navigate for Fine-grained Classificationcited by 103
  11. 2018Part-Aligned Bilinear Representations for Person Re-identificationcited by 90
  12. 2020Learning Attentive Pairwise Interaction for Fine-Grained Classificationcited by 84
  13. 2019Interaction-and-Aggregation Network for Person Re-identificationcited by 80
  14. 2016Discovering Causal Signals in Imagescited by 79
  15. 2018Confounding-Robust Policy Improvementcited by 73
  16. 2017Deeply-Learned Part-Aligned Representations for Person Re-Identificationcited by 68
  17. 2019Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom Upcited by 66
  18. 2019Mixed High-Order Attention Network for Person Re-Identificationcited by 65
  19. 2018Multi-Attention Multi-Class Constraint for Fine-grained Image Recognitioncited by 58
  20. 2019See Better Before Looking Closer: Weakly Supervised Data Augmentation Network for Fine-Grained Visual Classificationcited by 56
  21. 2018Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identificationcited by 55
  22. 2019Auto-ReID: Searching for a Part-aware ConvNet for Person Re-Identificationcited by 51
  23. 2018Dual Attention Matching Network for Context-Aware Feature Sequence based Person Re-Identificationcited by 50
  24. 2018Attention-Aware Compositional Network for Person Re-identificationcited by 50
  25. 2019Vehicle Re-identification with Viewpoint-aware Metric Learningcited by 45
  26. 2016End-to-End Comparative Attention Networks for Person Re-identificationcited by 42
  27. 2018Spectral Feature Transformation for Person Re-identificationcited by 39
  28. 2017Quality Aware Network for Set to Set Recognitioncited by 36
  29. 2019A Dual-Path Model With Adaptive Attention For Vehicle Re-Identificationcited by 34
  30. 2018Challenges of Using Text Classifiers for Causal Inferencecited by 33
  31. 2014Attention for Fine-Grained Categorizationcited by 15
  32. 2018Learning Region Features for Object Detectioncited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 21; 2023: 21; 2024: 28; 2025: 22; 2026: 18.

114 papers.

Sort:

By area:

  1. 2022CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labelscited by 177
  2. 2022Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identificationcited by 78
  3. 2022Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondencecited by 69
  4. 2025CF-VLM:CounterFactual Vision-Language Fine-tuningcited by 57
  5. 2023PLIP: Language-Image Pre-training for Person Representation Learningcited by 49
  6. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  7. 2024Magic Tokens: Select Diverse Tokens for Multi-modal Object Re-Identificationcited by 34
  8. 2023TOP-ReID: Multi-spectral Object Re-Identification with Token Permutationcited by 31
  9. 2023GaitGCI: Generative Counterfactual Intervention for Gait Recognitioncited by 30
  10. 2024DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identificationcited by 29
  11. 2022MetaFormer: A Unified Meta Framework for Fine-Grained Recognitioncited by 28
  12. 2023GeoDTR+: Toward generic cross-view geolocalization via geometric disentanglementcited by 27
38 more
  1. 2023Fine-grained Visual Classification with High-temperature Refinement and Background Suppressioncited by 22
  2. 2022SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorizationcited by 21
  3. 2024MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Promptcited by 20
  4. 2025Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoningcited by 20
  5. 2022SIM-Trans: Structure Information Modeling Transformer for Fine-grained Visual Categorizationcited by 19
  6. 2022Counterfactual Intervention Feature Transfer for Visible-Infrared Person Re-identificationcited by 18
  7. 2023Fine-grained Recognition with Learnable Semantic Data Augmentationcited by 17
  8. 2024When Large Vision-Language Models Meet Person Re-Identificationcited by 15
  9. 2023Delving into Multimodal Prompting for Fine-grained Visual Classificationcited by 14
  10. 2021Weakly-Supervised Video Object Grounding via Causal Interventioncited by 13
  11. 2024Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentationcited by 12
  12. 2022A Novel Plug-in Module for Fine-Grained Visual Classificationcited by 11
  13. 2023Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identificationcited by 11
  14. 2023DiG-IN: Diffusion Guidance for Investigating Networks -- Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanationscited by 11
  15. 2022Clinically-Inspired Multi-Agent Transformers for Disease Trajectory Forecasting from Multimodal Datacited by 10
  16. 2023Dynamic Enhancement Network for Partial Multi-modality Person Re-identificationcited by 9
  17. 2024Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identificationcited by 9
  18. 2021Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systemscited by 8
  19. 2022Fine-Grained Visual Classification using Self Assessment Classifiercited by 8
  20. 2024ReMix: Training Generalized Person Re-identification on a Mixture of Datacited by 8
  21. 2025ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identificationcited by 8
  22. 2023Face Presentation Attack Detection by Excavating Causal Clues and Adapting Embedding Statisticscited by 7
  23. 2025Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identificationcited by 7
  24. 2025MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identificationcited by 7
  25. 2021Making a Bird AI Expert Work for You and Mecited by 6
  26. 2022Counterfactual Multihop QA: A Cause-Effect Approach for Reducing Disconnected Reasoningcited by 6
  27. 2023Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-IDcited by 6
  28. 2023Rethinking Person Re-identification from a Projection-on-Prototypes Perspectivecited by 6
  29. 2024Enhancing person re-identification via Uncertainty Feature Fusion Method and Auto-weighted Measure Combinationcited by 6
  30. 2025Towards All-in-One Medical Image Re-Identificationcited by 6
  31. 2022Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularizationcited by 5
  32. 2022RVSL: Robust Vehicle Similarity Learning in Real Hazy Scenes Based on Semi-supervised Learningcited by 5
  33. 2024Pose-dIVE: Pose-Diversified Augmentation with Diffusion Model for Person Re-Identificationcited by 5
  34. 2025Neighbor-Based Feature and Index Enhancement for Person Re-Identificationcited by 5
  35. 2025NEXT: Multi-Grained Mixture of Experts via Text-Modulation for Multi-Modal Object Re-Identificationcited by 5
  36. 2022Fine-grained Activities of People Worldwidecited by 4
  37. 2022A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigmscited by 4
  38. 2024Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformerscited by 4

50 most cited of 114 All 114 (JSON)