Research map / Label-efficient and robust learning / Recognition and long-tail
Weakly Supervised Posture Mining for Fine-Grained Classification
Zhenchao Tang, Hualin Yang, Calvin Yu-Chian Chen
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 |
|---|---|---|---|
| replace direct node-feature concatenation with message passing (ablation) | PMRC (ResNet50, 6 regions) · CUB-200-2011 | Top-1 accuracy (%): +2.7 (91.8 vs 89.1) | Improved |
| replace CE with RCE loss for the whole-graph classification (ablation) | PMRC (ResNet50, 6 regions) · CUB-200-2011 | Top-1 accuracy (%): +1.2 (91.8 vs 90.6) | Improved |
| replace CE with RCE loss (ablation) | PMRC (SwinTransformer) · CUB-200-2011 | Top-1 accuracy (%): +0.8 (94.3 vs 93.5) | Improved |
| replace CE with RCE loss when training the plain backbone (ablation) | ResNet50 backbone · CUB-200-2011 | Top-1 accuracy (%): +1.2 (85.7 vs 84.5) | Improved |
| apply RCE instead of CE to a range of existing fine-grained models | ResNet50, DenseNet161, Xception, Inception-V3, MobileNetV2, B-CNN, NTS-Net and others · CUB, Cars, Aircraft, Dogs | Top-1 accuracy increment vs CE: mostly +0.4 to +2.1; DATL -0.28 on CUB, -0.19 on Aircraft, TResNet-L-V2 -0.07 on CUB | Mixed |
| add RCE loss and posture-mining graph (weakly supervised, image labels only) | PMRC (SwinTransformer) vs SwinTransformer backbone · CUB-200-2011 | Top-1 accuracy (%): +4.0 (94.3 vs 90.3) | Improved |
| add PMRC graph/posture framework on ResNet50 backbone | ResNet50 · CUB-200-2011 | Top-1 accuracy (%): +7.3 (91.8 vs 84.5) | Improved |
| varying number of discriminative regions (3 to 8) (ablation) | PMRC (ResNet50, message passing, RCE) · CUB-200-2011 | Top-1 accuracy (%): peak at 6 regions (91.8); 3 regions 90.9, 8 regions 91.4 | Mixed |
Closest papers by meaning
- Webly Supervised Fine-Grained Recognition: Benchmark Datasets and an Approach (ICCV 2021 · similarity 0.83)
- Fine-grained Classes and How to Find Them (ICML 2024 · similarity 0.83)
- Learning to Navigate for Fine-grained Classification (ECCV 2018 · similarity 0.83)
- The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition (ECCV 2016 · similarity 0.82)
- Unsupervised Magnification of Posture Deviations Across Subjects (CVPR 2020 · similarity 0.82)
- Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification (AAAI 2025 · similarity 0.81)
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.
