相关论文: PACE: Posthoc Architecture-Agnostic Concept Extrac…

This paper introduces the Pandemic PACT Advanced Categorisation Engine (PPACE) along with its associated dataset. PPACE is a fine-tuned model developed to automatically classify research abstracts from funded biomedical projects according…

This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained. The paper starts with describing the explainable neural network…

Providing explanations along with predictions is crucial in some text processing tasks. Therefore, we propose a new self-interpretable model that performs output prediction and simultaneously provides an explanation in terms of the presence…

Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To…

Concept Bottleneck Models (CBMs) have recently been proposed to address the 'black-box' problem of deep neural networks, by first mapping images to a human-understandable concept space and then linearly combining concepts for…

Due to their black-box and data-hungry nature, deep learning techniques are not yet widely adopted for real-world applications in critical domains, like healthcare and justice. This paper presents Memory Wrap, a plug-and-play extension to…

We propose a Convolutional Neural Network-based approach to learn, detect,and extract patterns in sequential trajectory data, known here as Social Pattern Extraction Convolution (Social-PEC). A set of experiments carried out on the human…

Deep convolutional neural networks (CNN) proved to be highly accurate to perform anatomical segmentation of medical images. However, some of the most popular CNN architectures for image segmentation still rely on post-processing strategies…

Counterfactual explanations (CEs) aim to enhance the interpretability of machine learning models by illustrating how alterations in input features would affect the resulting predictions. Common CE approaches require an additional model and…

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would help answer the question of what a deep learning system internally detects as relevant in the input, demystifying…

As artificial intelligence increasingly drives critical decisions, the ability to genuinely explain how neural networks make predictions is essential for trust. Yet, most current explanation methods offer post-hoc rationalizations rather…

Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering DNN-based approaches is improving their explainability. In this work we present CME: a concept-based model extraction…

Ensuring trustworthiness in open-world visual recognition requires models that are interpretable, fair, and robust to distribution shifts. Yet modern vision systems are increasingly deployed as proprietary black-box APIs, exposing only…

Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex…

Convolutional Neural Networks (CNNs) continue to achieve great success in classification tasks as innovative techniques and complex multi-path architecture topologies are introduced. Neural Architecture Search (NAS) aims to automate the…

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In…

The interpretability of model has become one of the obstacles to its wide application in the high-stake fields. The usual way to obtain interpretability is to build a black-box first and then explain it using the post-hoc methods. However,…

EXplainable AI (XAI) is an essential topic to improve human understanding of deep neural networks (DNNs) given their black-box internals. For computer vision tasks, mainstream pixel-based XAI methods explain DNN decisions by identifying…

Deep neural networks have shown exceptional performance in various tasks, but their lack of robustness, reliability, and tendency to be overconfident pose challenges for their deployment in safety-critical applications like autonomous…

The success of deep neural networks for pan-sharpening is commonly in a form of black box, lacking transparency and interpretability. To alleviate this issue, we propose a novel model-driven deep unfolding framework with image reasoning…