Post-hoc Part-prototype Networks
Post-hoc explainability methods such as Grad-CAM are popular because they do not influence the performance of a trained model. However, they mainly reveal "where" a model looks at for a given input, fail to explain "what" the model looks for (e.g., what is important to classify a bird image to a Scott Oriole?). Existing part-prototype networks leverage part-prototypes (e.g., characteristic Scott Oriole's wing and head) to answer both "where" and "what", but often under-perform their black box counterparts in the accuracy. Therefore, a natural question is: can one construct a network that answers both "where" and "what" in a post-hoc manner to guarantee the model's performance? To this end, we propose the first post-hoc part-prototype network via decomposing the classification head of a trained model into a set of interpretable part-prototypes. Concretely, we propose an unsupervised prototype discovery and refining strategy to obtain prototypes that can precisely reconstruct the classification head, yet being interpretable. Besides guaranteeing the performance, we show that our network offers more faithful explanations qualitatively and yields even better part-prototypes quantitatively than prior part-prototype networks.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Evaluating the effects of interactivity in a post-editing workbench
This paper describes the field trial and subsequent evaluation of a post-editing workbench which is currently under development in the EU-funded CasMaCat project. Based on user evaluations of the initial prototype of the…
Machine TranslationProtGNN: Towards Self-Explaining Graph Neural Networks
Despite the recent progress in Graph Neural Networks (GNNs), it remains challenging to explain the predictions made by GNNs. Existing explanation methods mainly focus on post-hoc explanations where another explanatory mo…
Graph Neural NetworkEnhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypes
Vertebral fracture grading classifies the severity of vertebral fractures, which is a challenging task in medical imaging and has recently attracted Deep Learning (DL) models. Only a few works attempted to make such mode…
DiversityMedical DiagnosisProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions …
But that's not why: Inference adjustment by interactive prototype revision
Despite significant advances in machine learning, decision-making of artificial agents is still not perfect and often requires post-hoc human interventions. If the prediction of a model relies on unreasonable factors it …
BIG-bench Machine LearningDecision Making