Research map / Label-efficient and robust learning / Recognition and long-tail
Counterfactual Attention Learning for Fine-Grained Visual Categorization and Re-Identification
Yongming Rao, Guangyi Chen, Jiwen Lu, Jie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add counterfactual attention learning | multi-head attention baseline · CUB200-2011 | top-1 accuracy: 89.3 -> 90.6 | Improved |
| add counterfactual attention learning | multi-head attention baseline · Stanford Cars | top-1 accuracy: 94.0 -> 95.5 | Improved |
| add counterfactual attention learning | multi-head attention baseline · FGVC Aircraft | top-1 accuracy: 93.6 -> 94.2 | Improved |
| add counterfactual attention learning | ResNet50 attention baseline · MSMT17 | mAP: 50.5 -> 56.2 | Improved |
| add counterfactual attention learning | ResNet50 attention baseline · Market1501 | mAP: 85.9 -> 87.0 | Improved |
| add counterfactual attention learning | ResNet50 attention baseline · DukeMTMC-ReID | mAP: 74.0 -> 76.4 | Improved |
| add counterfactual attention learning | ResNet50 attention baseline · VehicleID (test 800) | Rank-1: 76.7 -> 82.5 | Improved |
| add counterfactual attention learning | ResNet50 attention baseline · VeRi-776 | mAP: 72.0 -> 74.3 | Improved |
| use reversed attention as the counterfactual instead of random (ablation) | CAL · CUB200-2011 | top-1 accuracy: 90.6 -> 89.2 | Hurt |
| use uniform attention as the counterfactual instead of random (ablation) | CAL · CUB200-2011 | top-1 accuracy: 90.6 -> 90.2 | No clear effect |
| use shuffle attention as the counterfactual instead of random (ablation) | CAL · CUB200-2011 | top-1 accuracy: 90.6 -> 90.4 | No clear effect |
| add attention dropout instead of CAL (ablation) | attention baseline · CUB200-2011 | top-1 accuracy: 89.3 -> 88.9 | Hurt |
Closest papers by meaning
- Dual Cross-Attention Learning for Fine-Grained Visual Categorization and Object Re-Identification (CVPR 2022 · similarity 0.88)
- Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism (ECCV 2022 · similarity 0.87)
- Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition (CVPR 2025 · similarity 0.85)
- Rethinking Visual Counterfactual Explanations Through Region Constraint (ICLR 2025 · similarity 0.85)
- Learning 1D Causal Visual Representation with De-focus Attention Networks (NeurIPS 2024 · similarity 0.84)
- See What You Are Told: Visual Attention Sink in Large Multimodal Models (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
