In this paper, we run two methods of explanation, namely LIME and Grad-CAM, on a convolutional neural network trained to label images with the LEGO bricks that are visible in them. We evaluate them on two criteria, the improvement of the network's core performance and the trust they are able to generate for users of the system. We find that in general, Grad-CAM seems to outperform LIME on this specific task: it yields more detailed insight from the point of view of core performance and 80\% of respondents asked to choose between them when it comes to the trust they inspire in the model choose Grad-CAM. However, we also posit that it is more useful to employ these two methods together, as the insights they yield are complementary.
The performance of modern algorithms on certain computer vision tasks such as object recognition is now close to that of humans. This success was achieved at the price of complicated architectures depending on millions of parameters and it has become quite challenging to understand how particular predictions are made. Interpretability methods propose to give us this understanding. In this paper, we study LIME, perhaps one of the most popular. On the theoretical side, we show that when the number of generated examples is large, LIME explanations are concentrated around a limit explanation for w…
National Technical University of Athens（雅典国家技术大学）；Athena Research Center（雅典娜研究中心）
Although deep neural networks hold the state-of-the-art in several remote sensing tasks, their black-box operation hinders the understanding of their decisions, concealing any bias and other shortcomings in datasets and model performance. To this end, we have applied explainable artificial intelligence (XAI) methods in remote sensing multi-label classification tasks towards producing human-interpretable explanations and improve transparency. In particular, we utilized and trained deep learning models with state-of-the-art performance in the benchmark BigEarthNet and SEN12MS datasets. Ten XAI m…
SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction
Stockholm University（斯德哥尔摩大学）；Skatturinn (Iceland Revenue and Customs)（冰岛税务总局（冰岛税收和海关局））
On the Effectiveness of Methods and Metrics for Explainable AI in Remote Sensing Image Scene Classification
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（电气工程与计算机科学学院，技术大学柏林）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究院）
University of Augsburg（奥格斯堡大学）；University Hospital Augsburg（奥格斯堡大学医院）
In this work we use the AUCMEDI-Framework to train a deep neural network to classify chest X-ray images as either normal or viral pneumonia. Stratified k-fold cross-validation with k=3 is used to generate the validation-set and 15% of the data are set aside for the evaluation of the models of the different folds and ensembles each. A random-forest ensemble as well as a Soft-Majority-Vote ensemble are built from the predictions of the different folds. Evaluation metrics (Classification-Report, macro f1-scores, Confusion-Matrices, ROC-Curves) of the individual folds and the ensembles show that t…
Explaining a classification result produced by an image- and video-classification model is one of the important but challenging issues in computer vision. Many methods have been proposed for producing heat-map--based explanations for this purpose, including ones based on the white-box approach that uses the internal information of a model (e.g., LRP, Grad-CAM, and Grad-CAM++) and ones based on the black-box approach that does not use any internal information (e.g., LIME, SHAP, and RISE). We propose a new black-box method BOREx (Bayesian Optimization for Refinement of visual model Explanation) …
Are Explanations Helpful? A Comparative Analysis of Explainability Methods in Skin Lesion Classifiers
Instituto de Computação, Universidade Estadual de Campinas (UNICAMP), Campinas, Brazil（坎皮纳斯州立大学计算研究所（UNICAMP））；Department of Computer Science, Universidad Católica San Pablo, Arequipa, Peru（天主教圣巴布罗大学计算机科学系）；Department of Diabetes, Endocrinology, Nutritional Medicine and Metabolism UDEM, University of Bern, Switzerland（伯尔尼大学糖尿病、内分泌学、营养医学和代谢学系）
City Data Science Institute - City, University of London（伦敦城市大学城市数据科学研究所）
A novel explainable AI method called CLEAR Image is introduced in this paper. CLEAR Image is based on the view that a satisfactory explanation should be contrastive, counterfactual and measurable. CLEAR Image explains an image's classification probability by contrasting the image with a corresponding image generated automatically via adversarial learning. This enables both salient segmentation and perturbations that faithfully determine each segment's importance. CLEAR Image was successfully applied to a medical imaging case study where it outperformed methods such as Grad-CAM and LIME by an a…
BrainFusionNet: a deep learning and XAI model to understand local, global, and sequential features of MRI images for improved brain tumour detection
School of Mathematics, Physics and Computing, University of Southern Queensland（南方昆士兰大学数学、物理与计算学院）；School of Engineering, University of Southern Queensland（南方昆士兰大学工程学院）
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）
ConMatFormer: A Multi-attention and Transformer Integrated ConvNext based Deep Learning Model for Enhanced Diabetic Foot Ulcer Classification
Department of Information Technology（信息科技系）；Charles Darwin University（查尔斯·达尔文大学）；Department of Computer Science and Engineering（计算机科学与工程系）；University of Liberal Arts Bangladesh（孟加拉自由大学）；BRAC University（BRAC大学）；Center for Advanced Analytics (CAA), COE for Artificial Intelligence, Faculty of Engineering & Technology (FET)（高级分析中心（CAA）、人工智能学院、工程与技术学院）；Multimedia University Melaka（马六甲多媒体大学）；American International University-Bangladesh（美国国际大学-孟加拉）
From Explanations to Architecture: Explainability-Driven CNN Refinement for Brain Tumor Classification in MRI
American International Brac University Faculty of Psychology University-Bangladesh（美国国际布拉大学心理学学院（孟加拉国））；Shinawatra University Department of Computer Science（辛纳瓦特大学计算机科学系）；American International North South University（美国国际北南大学）；American International University–Bangladesh Department of Computer Science（美国国际大学–孟加拉国计算机科学系）；Multimedia University Department of Computer Science（多媒体大学计算机科学系）
University of Delhi（德里大学）；Hansraj College（汉斯raj学院）；Saral Diagnostics（Saral诊断中心）
Coronaviruses constitute a family of viruses that gives rise to respiratory diseases. As COVID-19 is highly contagious, early diagnosis of COVID-19 is crucial for an effective treatment strategy. However, the RT-PCR test which is considered to be a gold standard in the diagnosis of COVID-19 suffers from a high false-negative rate. Chest X-ray (CXR) image analysis has emerged as a feasible and effective diagnostic technique towards this objective. In this work, we propose the COVID-19 classification problem as a three-class classification problem to distinguish between COVID-19, normal, and pne…
A Novel Hybrid Deep Learning and Chaotic Dynamics Approach for Thyroid Cancer Classification
Laboratory of Renewable Energy, Department of Electronics, University of Jijel（可再生能源实验室，电子系，杰吉尔大学）；Non-Destructive Testing Laboratory, Department of Electronics, University of Jijel（无损检测实验室，电子系，杰吉尔大学）；Institute of Technology, University Center Salhi Ahmed（技术学院，Salhi Ahmed大学中心）；College of Engineering and Information Technology, University of Dubai（工程与信息科技学院，迪拜大学）
