arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.13909cs.LGcs.AIcs.CVstat.ML
收藏

概念嵌入分析综述

Concept Embedding Analysis: A Review

Continental AG(大陆集团)

Gesina Schwalbe

摘要:

深度神经网络(DNN)已经进入了许多应用领域,对人机系统的安全性、安全性和公平性产生了潜在的影响。这需要用户的基本理解和充分信任。这激发了可解释人工智能(XAI)的研究领域,即寻找打开DNN所代表的“黑匣子”的方法。对于具体的计算机视觉领域,DNN的实际评估需要将人类可解释的概念与模型的内部结构进行全局有效的关联。概念(嵌入)分析(CA)的研究领域解决了这个问题:CA旨在找到人类可解释的语义概念(例如,眼睛,胡须)与DNN的内部表示。这项工作建立了CA的一般定义和CA方法的分类,从文献中的几个想法相结合。这使得我们可以轻松地定位和比较保护性耕作方法。定义的概念的指导下,目前国家的最先进的研究,关于CA方法和有趣的应用程序进行了审查。三十多个相关的方法进行了讨论,比较和分类。最后,对于从业者来说,提供了对已用于监督概念分析的十五个数据集的调查。最后指出了面临的挑战和研究方向。

英文摘要:

Deep neural networks (DNNs) have found their way into many applications with potential impact on the safety, security, and fairness of human-machine-systems. Such require basic understanding and sufficient trust by the users. This motivated the research field of explainable artificial intelligence (XAI), i.e. finding methods for opening the "black-boxes" DNNs represent. For the computer vision domain in specific, practical assessment of DNNs requires a globally valid association of human interpretable concepts with internals of the model. The research field of concept (embedding) analysis (CA) tackles this problem: CA aims to find global, assessable associations of humanly interpretable semantic concepts (e.g., eye, bearded) with internal representations of a DNN. This work establishes a general definition of CA and a taxonomy for CA methods, uniting several ideas from literature. That allows to easily position and compare CA approaches. Guided by the defined notions, the current state-of-the-art research regarding CA methods and interesting applications are reviewed. More than thirty relevant methods are discussed, compared, and categorized. Finally, for practitioners, a survey of fifteen datasets is provided that have been used for supervised concept analysis. Open challenges and research directions are pointed out at the end.

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。

↑