梳理视觉模型概念解释方法，指明未来研究方向
Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?
- 从概念选择、表示到控制三方面系统分析解释方法
- 指出当前研究对概念可控性关注不足
- 建议借鉴知识表示学习提升解释能力
概念基础的可解释人工智能（C-XAI）在计算机视觉领域具有广阔前景，因其能以语义上有意义的图像部分作为解释单元，比仅标注显著区域的热力图更直观。近年来该领域进展迅速，亟需对现有成果进行系统回顾与反思。本文综述了当前主流的C-XAI方法，聚焦三个核心方向：解释所用概念的选择、概念的表示方式，以及如何对概念进行控制。针对概念控制问题，本文提出新方法并借鉴知识表示与学习领域的思想，为未来研究提供新思路。
原文摘要 · Abstract (English)
Concept-based XAI (C-XAI) approaches to explaining neural vision models are a promising field of research, since explanations that refer to concepts (i.e., semantically meaningful parts in an image) are intuitive to understand and go beyond saliency-based techniques that only reveal relevant regions. Given the remarkable progress in this field in recent years, it is time for the community to take a critical look at the advances and trends. Consequently, this paper reviews C-XAI methods to identify interesting and underexplored areas and proposes future research directions. To this end, we consider three main directions: the choice of concepts to explain, the choice of concept representation, and how we can control concepts. For the latter, we propose techniques and draw inspiration from the field of knowledge representation and learning, showing how this could enrich future C-XAI research.
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。