解决CLIP在概念定位中幻觉问题，提升解释可信度
Enhancing Concept Localization in CLIP-based Concept Bottleneck Models
- 用局部可解释性分离图像特征，定位目标概念像素
- 实验证明可降低概念误判率，提升解释忠实性
- 适合需要高可信解释的医疗、金融等敏感领域
本文从可解释人工智能视角出发，研究无需显式概念标注的基于CLIP的Concept Bottleneck Models（CBMs）。我们发现，这些方法依赖的CLIP在零样本场景下易产生概念幻觉，错误判断图像中概念是否存在，从而削弱解释的可信度。为此，提出概念幻觉抑制机制CHILI，通过解耦图像嵌入并精确定位目标概念对应像素，实现更精准的概念定位。该方法还支持生成基于显著性的可解释性输出，显著提升解释的可读性与可靠性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。