AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Support and Trivial Prototypes for Interpretable Image Classification

Chong Wang, Yuyuan Liu, Yuanhong Chen, Fengbei Liu, Yu Tian, Davis McCarthy, Helen Frazer, Gustavo Carneiro

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 51 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add closeness loss to learn support prototypes near the classification boundary (ablation)ProtoPNet (ResNet50) · CUB (full)accuracy (%): 86.5 -> 87.5Improved
Add discrimination loss to trivial prototypes (ablation)ProtoPNet (ResNet50) · CUB (full)accuracy (%): 86.5 -> 87.2Improved
Add closeness loss (ablation)ProtoPNet (ResNet34) · Stanford Dogs (full)accuracy (%): 80.9 -> 83.0Improved
Combine support and trivial branches (ST-ProtoPNet) instead of support branch alone (ablation)ST-ProtoPNet (VGG19) · CUB-200-2011 (cropped)accuracy (%): 81.8 -> 83.2Improved
Use two different prototype types instead of ensembling two same-type branches (support ensemble) (ablation)ST-ProtoPNet (VGG19) · CUB-200-2011 (cropped)accuracy (%): 82.4 -> 83.2Improved
Use support prototypes instead of trivial prototypes (Trivial ProtoPNet vs Support ProtoPNet) (ablation)ProtoPNet (VGG19) · CUB-200-2011 (cropped)accuracy (%): 81.2 -> 81.8Improved
Add support prototypes to improve interpretabilityProtoPNet (VGG19) · CUB (full) content heatmapCH (%): 48.66 -> 66.43 (ST-ProtoPNet)Improved
Combine support and trivial prototypes versus support only on IoU (ablation)ST-ProtoPNet (VGG19) · CUB (full)IoU (%): 42.04 -> 41.05Hurt
Use ST-ProtoPNet versus non-interpretable baseline on Cars with ResNet backbonesST-ProtoPNet (ResNet34) · Stanford Cars (cropped)accuracy (%): 92.6 -> 91.4Hurt
Use 40 prototypes per class rather than 10 for ST-ProtoPNet (ablation)ST-ProtoPNet (VGG16) · CUB (full)accuracy (%): 76.8 -> 81.0Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy