Research map / Label-efficient and robust learning / Recognition and long-tail
Interpretable Image Classification with Differentiable Prototypes Assignment
Dawid Rymarczyk, Łukasz Struski, Michał Górszczak, Koryna Lewandowska, Jacek Tabor, Bartosz Zieliński
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 orthogonalization loss (ablation) | ProtoPool · CUB-200-2011 | accuracy: 82.4 -> 85.5 | Improved |
| add orthogonalization loss (ablation) | ProtoPool · Stanford Cars | accuracy: 86.8 -> 88.9 | Improved |
| use Gumbel-Softmax instead of softmax (ablation) | ProtoPool · CUB-200-2011 | accuracy: 80.3 -> 85.5 | Improved |
| use Gumbel-Softmax instead of softmax (ablation) | ProtoPool · Stanford Cars | accuracy: 64.5 -> 88.9 | Improved |
| add Gumbel-Softmax and orthogonalization loss together (ablation) | ProtoPool · CUB-200-2011 | accuracy: 65.1 -> 85.5 | Improved |
| add Gumbel-Softmax and orthogonalization loss together (ablation) | ProtoPool · Stanford Cars | accuracy: 30.8 -> 88.9 | Improved |
| use focal similarity instead of ProtoPNet similarity (ablation) | ProtoPool · CUB-200-2011 | accuracy: 85.3 -> 85.5 | No clear effect |
| use focal similarity instead of ProtoPNet similarity (ablation) | ProtoPool · Stanford Cars | accuracy: 88.8 -> 88.9 | No clear effect |
| apply prototype projection (ablation) | ProtoPool ResNet34 · CUB-200-2011 | accuracy: 80.8 -> 80.3 | No clear effect |
| apply prototype projection (ablation) | ProtoPool ResNet50 · Stanford Cars | accuracy: 88.4 -> 88.9 | No clear effect |
| use ProtoPool instead of ProtoPShare with fewer prototypes | ResNet34 · CUB-200-2011 | accuracy: 74.7 -> 80.3 | Improved |
| use ProtoPool instead of TesNet with 10x fewer prototypes | ResNet34 · Stanford Cars | accuracy: 92.6 -> 89.3 | Hurt |
Closest papers by meaning
- Interpretable Image Classification via Non-parametric Part Prototype Learning (CVPR 2025 · similarity 0.89)
- Interpretable Image Classification with Adaptive Prototype-based Vision Transformers (NeurIPS 2024 · similarity 0.89)
- ProtoArgNet: Interpretable Image Classification with Super-Prototypes and Argumentation (AAAI 2025 · similarity 0.88)
- Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining (ICML 2024 · similarity 0.88)
- A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations (AAAI 2025 · similarity 0.87)
- MCPNet: An Interpretable Classifier via Multi-Level Concept Prototypes (CVPR 2024 · similarity 0.85)
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.
