Papers › Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining

Improving Prototypical Visual Explanations with Reward Reweighing, Reselection, and Retraining

8 Jul 2023arXiv:2307.03887archive 2025-07-28

Aaron J. Li, Robin Netzorg, Zhihan Cheng, Zhuoqin Zhang, Bin Yu

In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network (ProtoPNet), which attempts to classify images based on meaningful parts of the input. While this architecture is able to produce visually interpretable classifications, it often learns to classify based on parts of the image that are not semantically meaningful. To address this problem, we propose the Reward Reweighing, Reselecting, and Retraining (R3) post-processing framework, which performs three additional corrective updates to a pretrained ProtoPNet in an offline and efficient manner. The first two steps involve learning a reward model based on collected human feedback and then aligning the prototypes with human preferences. The final step is retraining, which realigns the base features and the classifier layer of the original model with the updated prototypes. We find that our R3 framework consistently improves both the interpretability and the predictive accuracy of ProtoPNet and its variants.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

aaron-jx-li/r3-protopnet officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNBASE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections