AI Paper Atlas

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

This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations

Chiyu Ma, Brandon Zhao, Chaofan Chen, Cynthia Rudin

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Self-explaining and visual explanation networks · 4 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
Replace single-patch prototypes with ball-shaped concepts shown through multiple training patchesProtoPNet, ProtoPool, and TesNet · CUB 200-2011 testaccuracy: 77.9 ± 0.2 vs 78.0 ± 0.2; 78.2 ± 0.8 vs 77.9 ± 0.1; 81.5 ± 0.6 vs 80.3 ± 0.3No clear effect
Use multiple visualizations of a prototypeProtoPNet explanations · User study class identificationaccuracy: 51.5 ± 5.2 -> 62.1 ± 5.4Improved
Set radius initialization to 4.0 instead of 4.5 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after pruning and fine-tuning: 85.2 ± 0.2 -> 81.5 ± 1.0Hurt
Set radius initialization to 5.0 instead of 4.5 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after pruning and fine-tuning: 85.2 ± 0.2 -> 85.0 ± 0.3No clear effect
Use top-k cluster loss with k=1 rather than k=10 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after fine-tuning: 85.2 ± 0.2 -> 67.7 ± 2.0Hurt
Increase top-k cluster loss k from 1 to 3 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after fine-tuning: 67.7 ± 2.0 -> 83.5 ± 0.5Improved
Increase top-k cluster loss k from 3 to 5 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after fine-tuning: 83.5 ± 0.5 -> 84.4 ± 0.3Improved
Increase top-k cluster loss k from 5 to 10 (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy after fine-tuning: 84.4 ± 0.3 -> 85.2 ± 0.2Improved
Use top-k cluster loss (ablation)ProtoPool-Concepts · CUB 200-2011, ResNet-50 (iNat)accuracy before pruning: 85.2 ± 0.3; 85.3 ± 0.3; 85.5 ± 0.1; 85.3 ± 0.3No clear effect

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