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, causality, and usability, which hinder their practical applications. In this paper, 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.
Honda Research Institute Europe（本田欧洲研究所）；David R. Cheriton School of Computer Science, University of Waterloo（滑铁卢大学大卫·R·切里顿计算机科学学院）
Current research on Explainable AI (XAI) heavily targets on expert users (data scientists or AI developers). However, increasing importance has been argued for making AI more understandable to nonexperts, who are expected to leverage AI techniques, but have limited knowledge about AI. We present a mobile application to support nonexperts to interactively make sense of Convolutional Neural Networks (CNN); it allows users to play with a pretrained CNN by taking pictures of their surrounding objects. We use an up-to-date XAI technique (Class Activation Map) to intuitively visualize the model's de…
Explainability of CNN Based Classification Models for Acoustic Signal
Department of Computer Science, Missouri State University（计算机科学系，密苏里州立大学）；Department of Biology, Missouri State University（生物学系，密苏里州立大学）；Biodiversity Research Institute（生物多样性研究学院）
We describe an extension of the Fanoos XAI system [Bayani et al 2022] which enables the system to learn the appropriate action to take in order to satisfy a user's request for description to be made more or less abstract. Specifically, descriptions of systems under analysis are stored in states, and in order to make a description more or less abstract, Fanoos selects an operator from a large library to apply to the state and generate a new description. Prior work on Fanoos predominately used hand-written methods for operator-selection; this current work allows Fanoos to leverage experience to …
The XAI literature is decentralized, both in terminology and in publication venues, but recent years saw the community converge around keywords that make it possible to more reliably discover papers automatically. We use keyword search using the SemanticScholar API and manual curation to collect a well-formatted and reasonably comprehensive set of 5199 XAI papers, available at https://github.com/alonjacovi/XAI-Scholar . We use this collection to clarify and visualize trends about the size and scope of the literature, citation trends, cross-field trends, and collaboration trends. Overall, XAI i…
Federal Office for Information Security (BSI)（联邦信息安全办公室）
The nondeterminism of Deep Learning (DL) training algorithms and its influence on the explainability of neural network (NN) models are investigated in this work with the help of image classification examples. To discuss the issue, two convolutional neural networks (CNN) have been trained and their results compared. The comparison serves the exploration of the feasibility of creating deterministic, robust DL models and deterministic explainable artificial intelligence (XAI) in practice. Successes and limitation of all here carried out efforts are described in detail. The source code of the atta…
Know-Center GmbH（Know-Center有限公司）；University of Technology Graz（格拉茨技术大学）
Deep learning models have recently demonstrated remarkable results in a variety of tasks, which is why they are being increasingly applied in high-stake domains, such as industry, medicine, and finance. Considering that automatic predictions in these domains might have a substantial impact on the well-being of a person, as well as considerable financial and legal consequences to an individual or a company, all actions and decisions that result from applying these models have to be accountable. Given that a substantial amount of data that is collected in high-stake domains are in the form of ti…
A XAI-based Framework for Frequency Subband Characterization of Cough Spectrograms in Chronic Respiratory Disease
Universidad de Valladolid（巴利亚多利德大学）；Universidad de Salamanca（萨拉曼卡大学）；CIP Technologies LTD（CIP技术有限公司）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Gerencia Regional de Salud de Castilla y León（卡斯蒂利亚-莱昂地区卫生局）
Should XAI Nudge Human Decisions with Explanation Biasing?
Tokyo Metropolitan University（东京都立大学）；National Institute of Informatics（信息学研究所）；The Graduate University for Advanced Studies (SOKENDAI)（高级研究大学院大学（SOKENDAI））
Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Science
Technische Universität Berlin（柏林工业大学）；ATB（莱布尼茨农业工程与生物经济研究所）；University of Leipzig（莱比锡大学）；University of Reading（雷丁大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所（BIFOLD））；UiT the Arctic University of Norway（挪威北极大学）；University of Potsdam（波茨坦大学）
LUT University（拉彭兰塔-拉赫蒂工业大学）；Norwegian University of Science and Technology（挪威科技大学）；SINTEF Digital（挪威科技工业研究院数字研究所）
The final search query for the Systematic Literature Review (SLR) was conducted on 15th July 2022. Initially, we extracted 1707 journal and conference articles from the Scopus and Web of Science databases. Inclusion and exclusion criteria were then applied, and 58 articles were selected for the SLR. The findings show four dimensions that shape the AI explanation, which are format (explanation representation format), completeness (explanation should contain all required information, including the supplementary information), accuracy (information regarding the accuracy of the explanation), and c…
Explainable Prediction of the Mechanical Properties of Composites with CNNs
Department of Mechanical Engineering, Imperial College London, UK（帝国理工学院机械工程系）；Department of Computing, Imperial College London, UK（帝国理工学院计算系）；Department of Informatics, King's College London, UK（伦敦国王学院信息学系）
UCLA（加州大学洛杉矶分校）；University of Michigan（密歇根大学）；Oregon State University（俄勒冈州立大学）；Beijing Institute for General AI (BIGAI)（北京通用人工智能研究院）；Tsinghua University（清华大学）；Peking University（北京大学）
We propose CX-ToM, short for counterfactual explanations with theory-of mind, a new explainable AI (XAI) framework for explaining decisions made by a deep convolutional neural network (CNN). In contrast to the current methods in XAI that generate explanations as a single shot response, we pose explanation as an iterative communication process, i.e. dialog, between the machine and human user. More concretely, our CX-ToM framework generates sequence of explanations in a dialog by mediating the differences between the minds of machine and human user. To do this, we use Theory of Mind (ToM) which …
RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework
East West University（东西大学）；American International University-Bangladesh（孟加拉国美国国际大学）；Bangladesh Army University of Engineering and Technology（孟加拉国陆军工程技术大学）
Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems
Queen’s University（女王大学）；Newcastle University（纽卡斯尔大学）；University of Stirling（斯特灵大学）；University of Parma（帕尔马大学）；Robert Gordon University（罗伯特戈登大学）；University of Trento（特伦托大学）；Universiteit Leiden（莱顿大学）；University of Exeter（埃克塞特大学）
A Lightweight CNN Integrated Compact Convolutional Transformer for Multi-Scale Feature Learning and reducing computational complexity for breast cancer mammography image detection and classification
VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis
Scientific Computing and Imaging Institute, University of Utah, USA（美国犹他大学科学计算与成像研究所）；University of California, Davis, USA（美国加州大学戴维斯分校）；Bosch Research North America and Bosch Center for Artificial Intelligence (BCAI), USA（美国博世北美研究部及博世人工智能中心）；Robert Bosch GmbH, Germany（德国博世集团）；Splunk Technology, USA（美国Splunk技术公司）
AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has succeeded the most, explainability is still poorly assessed. In the field of image recognition many feature attribution methods have been proposed with the purpose of explaining a model's behavior using visual cues. However, no metrics have been established so far to assess and select these methods objectively. In this paper we propose a consistent evaluation sco…
On the Role of Domain Experts in Creating Effective Tutoring Systems
Department of Computer Science, Colorado State University, USA（科罗拉多州立大学计算机科学系）；Colorado State University Extension, USA（科罗拉多州立大学扩展服务）；School of Education, Colorado State University, USA（科罗拉多州立大学教育学院）
University of Konstanz（康斯坦茨大学）；Offenburg University of Applied Sciences（奥芬堡应用科学大学）
Decision explanations of machine learning black-box models are often generated by applying Explainable AI (XAI) techniques. However, many proposed XAI methods produce unverified outputs. Evaluation and verification are usually achieved with a visual interpretation by humans on individual images or text. In this preregistration, we propose an empirical study and benchmark framework to apply attribution methods for neural networks developed for images and text data on time series. We present a methodology to automatically evaluate and rank attribution techniques on time series using perturbation…
ISTI-CNR（意大利国家研究委员会信息科学与技术研究所）；University of Pisa（比萨大学）；Criteo AI Lab（Criteo人工智能实验室）；Scuola Normale Superiore of Pisa（比萨高等师范学校）
A key issue in critical contexts such as medical diagnosis is the interpretability of the deep learning models adopted in decision-making systems. Research in eXplainable Artificial Intelligence (XAI) is trying to solve this issue. However, often XAI approaches are only tested on generalist classifier and do not represent realistic problems such as those of medical diagnosis. In this paper, we analyze a case study on skin lesion images where we customize an existing XAI approach for explaining a deep learning model able to recognize different types of skin lesions. The explanation is formed by…
A Comprehensive Guide to Explainable AI: From Classical Models to LLMs
National Tsing Hua University（国立清华大学）；Indiana University（印第安纳大学）；National University of Singapore（新加坡国立大学）；Kyoto University（京都大学）；AppCubic；Rutgers University（罗格斯大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Purdue University（普渡大学）；Georgia Institute of Technology（佐治亚理工学院）；National Taiwan Normal University（国立台湾师范大学）；University of Hawaii（夏威夷大学）；Xi’an Jiaotong-Liverpool University（西交利物浦大学）；Pingtan Research Institute of Xiamen University（厦门大学平潭研究院）；University of Manchester（曼彻斯特大学）；Aarhus University（奥胡斯大学）；Imperial College London（伦敦帝国学院）；School of Visual Arts（视觉艺术学院）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
XAI-SOH-FL: Enhancing SOH-FL with Adaptive Aggregation and Explainable AI for Intrusion Detection in Heterogeneous IoT
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST)（电气工程与计算机科学学院（SEECS），国家 sciences and Technology（NUST））
Peking University（北京大学）；The Hong Kong University of Science and Technology（香港科技大学）；Deepwise AI Lab（深智城人工智能实验室）
Automatic blood vessel extraction from 3D medical images is crucial for vascular disease diagnoses. Existing methods based on convolutional neural networks (CNNs) may suffer from discontinuities of extracted vessels when segmenting such thin tubular structures from 3D images. We argue that preserving the continuity of extracted vessels requires to take into account the global geometry. However, 3D convolutions are computationally inefficient, which prohibits the 3D CNNs from sufficiently large receptive fields to capture the global cues in the entire image. In this work, we propose a hybrid re…
Reliable or Deceptive? Investigating Gated Features for Smooth Visual Explanations in CNNs
Indian Institute of Information Technology Kalyani（印度卡利亚尼信息技术学院）；Jalpaiguri Government Engineering College（贾尔派古里政府工程学院）；Alipurduar Government Engineering and Management College（阿里布尔杜阿尔政府工程与管理学院）；Indian Institute of Technology Roorkee（鲁基印度理工学院）；Amazon（亚马逊）
Information and Computer Science, King Fahd University of Petroleum and Minerals（信息与计算机科学系，国王法赫德石油与矿物大学）；Faculty of Science and Information Technology, Daffodil International University（科学与信息技术学院，达福尔国际大学）；Department of Human Anatomy and Physiology, The Faculty of Health Sciences, University of Johannesburg（人类解剖学与生理学系，健康科学学院，约翰内斯堡大学）；Centre for Data Analytics（数据分析中心）；School of Psychology, Bond University（心理学学院，邦德大学）
Context: Mpox is a zoonotic disease caused by the Mpox virus, which shares similarities with other skin conditions, making accurate early diagnosis challenging. Artificial intelligence (AI), especially Deep Learning (DL), has a strong tool for medical image analysis; however, pre-trained models like CNNs and XAI techniques for mpox detection is underexplored. Objective: This study aims to evaluate the effectiveness of pre-trained CNN models (VGG16, VGG19, InceptionV3, MobileNetV2) for the early detection of monkeypox using binary and multi-class datasets. It also seeks to enhance model interpr…
LAG-XAI: A Lie-Inspired Affine Geometric Framework for Interpretable Paraphrasing in Transformer Latent Spaces
Khmelnytskyi National University（赫梅利尼茨基国立大学）；Taras Shevchenko National University of Kyiv（基辅塔拉斯·舍甫琴科国立大学）；V.M. Glushkov Institute of Cybernetics of NAS of Ukraine（乌克兰国家科学院V.M.格卢什科夫控制论研究所）
Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion. This research presents an explainable framework for detecting spam images using Convolutional Neural Network(CNN) algorithms and Explainable Artificial Intelligence (XAI) algorithms. In this work, we use CNN model to classify image spam respectively whereas the post-hoc XAI methods including Local Interpretable Model Agnostic Explanation (LIME) and Shapley Additive Explanations (SHAP) were deployed to provide explanations for the decisions that the black-box CNN models made abo…
