paper-with-me

Papers

Enhancing Concept Localization in CLIP-based Concept Bottleneck Models

2025-10-08 · Rémi Kazmierczak, Steve Azzolin, Eloïse Berthier, Goran Frehse, Gianni Franchi arxiv

This paper addresses explainable AI (XAI) through the lens of Concept Bottleneck Models (CBMs) that do not require explicit concept annotations, relying instead on concepts extracted using CLIP in a zero-shot manner. We show that CLIP, which is central in these techniques, is prone to concept hallucination, incorrectly predicting the presence or absence of concepts within an image in scenarios used in numerous CBMs, hence undermining the faithfulness of explanations. To mitigate this issue, we introduce Concept Hallucination Inhibition via Localized Interpretability (CHILI), a technique that disentangles image embeddings and localizes pixels corresponding to target concepts. Furthermore, our approach supports the generation of saliency-based explanations that are more interpretable.

📄 PDF Abstract BibTeX arXiv:2510.07115

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework

2025-09-02 · Furong Jia, Lanxin Liu, Ce Hou, Fan Zhang 외 arxiv

Worldwide geo-localization involves determining the exact geographic location of images captured globally, typically guided by geographic cues such as climate, landmarks, and architectural styles. Despite advancements in…

Contrastive Learning

Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning

2024-04-04 · Andrei Semenov, Vladimir Ivanov, Aleksandr Beznosikov, Alexander Gasnikov

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs). While SOTA approaches to Image Classification task work as a black box, there is a growing demand for models…

Contrastive Learningimage-classificationImage ClassificationInterpretable Machine Learning+1

Locality-aware Concept Bottleneck Model

2025-08-20 · Sujin Jeon, Hyundo Lee, Eungseo Kim, Sanghack Lee 외 arxiv

Concept bottleneck models (CBMs) are inherently interpretable models that make predictions based on human-understandable visual cues, referred to as concepts. As obtaining dense concept annotations with human labeling is…

Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts

2024-08-05 · Andong Tan, Fengtao Zhou, Hao Chen

The concept bottleneck model (CBM) is an interpretable-by-design framework that makes decisions by first predicting a set of interpretable concepts, and then predicting the class label based on the given concepts. Existi…

zero-shot-classificationZero-Shot Learning

Multimodal Concept Bottleneck Models

2026-06-18 · Tongqing Shi, Ge Yan, Tuomas Oikarinen, Tsui-Wei Weng arxiv

Concept Bottleneck Models (CBMs) enhance the interpretability of deep learning networks by aligning the features extracted from images with natural concepts. However, existing CBMs are constrained in their ability to gen…

Image Retrieval