Related papers: DXAI: Explaining Classification by Image Decomposi…

Image decomposition aims to analyze an image into elementary components, which is essential for numerous downstream tasks and also by nature provides certain interpretability to the analysis. Deep learning can be powerful for such tasks,…

Artificial Intelligence (XAI) has found numerous applications in computer vision. While image classification-based explainability techniques have garnered significant attention, their counterparts in semantic segmentation have been…

The remarkable success of deep learning has prompted interest in its application to medical imaging diagnosis. Even though state-of-the-art deep learning models have achieved human-level accuracy on the classification of different types of…

Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often…

Understanding intermediate layers of a deep learning model and discovering the driving features of stimuli have attracted much interest, recently. Explainable artificial intelligence (XAI) provides a new way to open an AI black box and…

Aligning machine representations with human understanding is key to improving interpretability of machine learning (ML) models. When classifying a new image, humans often explain their decisions by decomposing the image into concepts and…

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

Part-based image classification aims at representing categories by small sets of learned discriminative parts, upon which an image representation is built. Considered as a promising avenue a decade ago, this direction has been neglected…

This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system…

The recent statistical theory of neural networks focuses on nonparametric denoising problems that treat randomness as additive noise. Variability in image classification datasets does, however, not originate from additive noise but from…

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…

Image decomposition is a crucial subject in the field of image processing. It can extract salient features from the source image. We propose a new image decomposition method based on convolutional neural network. This method can be applied…

Deep learning (DL) has revolutionized the field of document image analysis, showcasing superhuman performance across a diverse set of tasks. However, the inherent black-box nature of deep learning models still presents a significant…

We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwork from the original full model, with compressed structure…

Current AI-based methods do not provide comprehensible physical interpretations of the utilized data, extracted features, and predictions/inference operations. As a result, deep learning models trained using high-resolution satellite…

Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses the so-called counterfactual…

A main drawback of eXplainable Artificial Intelligence (XAI) approaches is the feature independence assumption, hindering the study of potential variable dependencies. This leads to approximating black box behaviors by analyzing the effects…

Not only automation of manufacturing processes but also automation of automation procedures itself become increasingly relevant to automation research. In this context, automated capability assessment, mainly leveraged by deep learning…

We present an algorithm, Decision-Directed Data Decomposition (D4), which decomposes a dataset into two components. The first contains most of the useful information for a specified supervised learning task. The second orthogonal component…

We introduce Discovering Conceptual Network Explanations (DCNE), a new approach for generating human-comprehensible visual explanations to enhance the interpretability of deep neural image classifiers. Our method automatically finds visual…