Research map / Label-efficient and robust learning / Recognition and long-tail
Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks
Qihan Huang, Mengqi Xue, Wenqi Huang, Haofei Zhang, Jie Song, Yongcheng Jing, Mingli Song
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 SA module to revised ProtoPNet (ablation) | Ours (revised ProtoPNet) · CUB-200-2011 (ResNet34) | consistency score: 52.9 -> 67.5 | Improved |
| add SDFA module on top of SA (ablation) | Ours + SA · CUB-200-2011 (ResNet34) | consistency score: 67.5 -> 70.6 | Improved |
| add SA module (ablation) | Ours (revised ProtoPNet) · CUB-200-2011 (ResNet34) | accuracy: 82.3 -> 83.6 | Improved |
| add SDFA module on top of SA (ablation) | Ours + SA · CUB-200-2011 (ResNet34) | accuracy: 83.6 -> 84.0 | Improved |
| add SDFA module (ablation) | Ours · CUB-200-2011 test set (ResNet34) | shallow-deep spatial structure similarity (%): 12.4 -> 70.8 | Improved |
| add SA module (ablation) | Ours · CUB-200-2011 (ResNet34) | avg similar prototypes from other categories: 3.9 -> 8.5 | Mixed |
| add SA and SDFA modules (ablation) | Ours · CUB-200-2011 (VGG19) | accuracy: 80.6 -> 82.5 | Improved |
| use full model versus best prior method TesNet | Ours + SA + SDFA · CUB-200-2011 (Dense121) | consistency score: 63.1 -> 68.1 | Mixed |
| vanilla ProtoPNet prototypes | ProtoPNet · CUB-200-2011 | consistency score: 15.1 to 31.6 across five backbones | Hurt |
| higher consistency and stability across part-prototype networks | part-prototype networks · CUB-200-2011 | accuracy | Improved |
Closest papers by meaning
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.92)
- Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanations (AAAI 2024 · similarity 0.90)
- Post-hoc Part-Prototype Networks (ICML 2024 · similarity 0.89)
- A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations (AAAI 2025 · similarity 0.87)
- Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time (CVPR 2025 · similarity 0.87)
- LucidPPN: Unambiguous Prototypical Parts Network for User-centric Interpretable Computer Vision (ICLR 2025 · similarity 0.87)
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.
