AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN

Sun, Changqi1,2; Xu, Hao3,4; Chen, Yuntian5; Zhang, Dongxiao2,5

2024-09-01

10.1002/aisy.202400359

ADVANCED INTELLIGENT SYSTEMS   影响因子和分区

2640-4567

["Explainable artificial intelligence (XAI) aims to develop transparent explanatory approaches for \"black-box\" deep learning models. However, it remains difficult for existing methods to achieve the trade-off of the three key criteria in interpretability, namely, reliability, understandability, and usability, which hinder their practical applications. In this article, we propose a self-supervised automatic semantic interpretable explainable artificial intelligence (AS-XAI) framework, which utilizes transparent orthogonal embedding semantic extraction spaces and row-centered principal component analysis (PCA) for global semantic interpretation of model decisions in the absence of human interference, without additional computational costs. In addition, the invariance of filter feature high-rank decomposition is used to evaluate model sensitivity to different semantic concepts. Extensive experiments demonstrate that robust and orthogonal semantic spaces can be automatically extracted by AS-XAI, providing more effective global interpretability for convolutional neural networks (CNNs) and generating human-comprehensible explanations. The proposed approach offers broad fine-grained extensible practical applications, including shared semantic interpretation under out-of-distribution (OOD) categories, auxiliary explanations for species that are challenging to distinguish, and classification explanations from various perspectives. In a systematic evaluation by users with varying levels of AI knowledge, AS-XAI demonstrated superior \"glass box\" characteristics.","Explainable artificial intelligence (XAI) provides transparent deep learning explanations. This article introduces self-supervised automatic semantic interpretable XAI (AS-XAI), a framework using orthogonal embedding spaces and principal component analysis (PCA) for global semantic interpretation, and offers effective interpretability for convolutional neural networks (CNNs), including out-of-distribution (OOD) category interpretation and species classification, with minimal computational cost.image (c) 2024 WILEY-VCH GmbH"]

convolutional neural network interpretable machine learning out-of-distribution detection self-supervised learning semantic space

SCI

英语

第一

National Center for Applied Mathematics Shenzhen[ZDSYS20200421111201738] ; SUSTech-Qingdao New Energy Technology Research Institute[62106116] ; National Natural Science Foundation of China[PCL2022A05]

Automation & Control Systems ; Computer Science ; Robotics

Automation & Control Systems ; Computer Science, Artificial Intelligence ; Robotics

WOS:001322069600001

WILEY

Web of Science

1.Southern Univ Sci & Technol, Sch Environm Sci & Engn, Shenzhen 518055, Guangdong, Peoples R China
2.Peng Cheng Lab, Dept Math & Theories, Shenzhen 518000, Guangdong, Peoples R China
3.Peking Univ, Coll Engn, BIC ESAT, ERE, Beijing 100871, Peoples R China
4.Peking Univ, SKLTCS, Coll Engn, Beijing 100871, Peoples R China
5.Eastern Inst Technol, Ningbo Inst Digital Twin, R China, Ningbo 315200, Zhejiang, Peoples R China

Sun, Changqi,Xu, Hao,Chen, Yuntian,et al. AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN[J]. ADVANCED INTELLIGENT SYSTEMS,2024.

Sun, Changqi,Xu, Hao,Chen, Yuntian,&Zhang, Dongxiao.(2024).AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN.ADVANCED INTELLIGENT SYSTEMS.

Sun, Changqi,et al."AS-XAI: Self-Supervised Automatic Semantic Interpretation for CNN".ADVANCED INTELLIGENT SYSTEMS (2024).