← Search

Amin Parchami-Araghi

2 accepted papers

2025

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

NeurIPS 2025poster

Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge. Many post-hoc concept-based approaches have been introduced to understand their workings, yet they are not always faithful to t…

Cited by 0SourceScholar
2023

Studying How to Efficiently and Effectively Guide Models with Explanations

ICCV 2023poster

Despite being highly performant, deep neural networks might base their decisions on features that spuriously correlate with the provided labels, thus hurting generalization. To mitigate this, 'model guidance' has recently gained popularity, i.e. the idea of regularizing the models' explanations to e…

Cited by 14PDFcodeScholar