增强基于CLIP的概念瓶颈模型中的概念定位
Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
AI总结：
本文提出CHILI方法，通过解耦图像嵌入并定位目标概念像素，抑制CLIP在概念瓶颈模型中的概念幻觉，生成更可解释的显著性解释。
摘要：
本文通过概念瓶颈模型（CBMs）的视角解决可解释人工智能（XAI）问题，这些模型不需要显式的概念标注，而是依赖于使用CLIP以零样本方式提取的概念。我们表明，CLIP作为这些技术的核心，容易产生概念幻觉，即在众多CBMs使用的场景中错误地预测图像内概念的存在或缺失，从而削弱了解释的忠实性。为缓解这一问题，我们引入了通过局部可解释性抑制概念幻觉（CHILI）的技术，该技术解耦图像嵌入并定位与目标概念对应的像素。此外，我们的方法支持生成更具可解释性的基于显著性的解释。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
