English
Related papers

Related papers: Invertible Concept-based Explanations for CNN Mode…

200 papers

With the rise of deep neural networks, especially in safety-critical applications, robustness and interpretability are crucial to ensure their trustworthiness. Recent advances in 3D-aware classifiers that map image features to volumetric…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Nhi Pham , Artur Jesslen , Bernt Schiele , Adam Kortylewski , Jonas Fischer

One of the most pressing challenges in artificial intelligence is to make models more transparent to their users. Recently, explainable artificial intelligence has come up with numerous method to tackle this challenge. A promising avenue is…

Machine Learning · Computer Science 2025-09-30 Julia Wenkmann , Damien Garreau

Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts. These methods typically find concept activation vectors…

Machine Learning · Computer Science 2024-08-19 Angus Nicolson , Yarin Gal , J. Alison Noble

This paper introduces Neuro-Activated Vision Explanations (NAVE), a method for extracting and visualizing the internal representations of vision model encoders. By clustering feature activations, NAVE provides insights into learned…

Computer Vision and Pattern Recognition · Computer Science 2025-07-15 Ahcène Boubekki , Samuel G. Fadel , Sebastian Mair

Convolutional neural networks have been shown to develop internal representations, which correspond closely to semantically meaningful objects and parts, although trained solely on class labels. Class Activation Mapping (CAM) is a recent…

Computer Vision and Pattern Recognition · Computer Science 2016-05-26 Amir Rosenfeld , Shimon Ullman

The interpretability of machine learning models has been an essential area of research for the safe deployment of machine learning systems. One particular approach is to attribute model decisions to high-level concepts that humans can…

Machine Learning · Computer Science 2022-09-14 Varsha Pendyala , Jihye Choi

In explainable AI, Concept Activation Vectors (CAVs) are typically obtained by training linear classifier probes to detect human-understandable concepts as directions in the activation space of deep neural networks. It is widely assumed…

Artificial Intelligence · Computer Science 2025-11-07 Jacob Lysnæs-Larsen , Marte Eggen , Inga Strümke

Interpretability methods for image classification assess model trustworthiness by attempting to expose whether the model is systematically biased or attending to the same cues as a human would. Saliency methods for feature attribution…

Machine Learning · Statistics 2021-04-08 Jacob Pfau , Albert T. Young , Jerome Wei , Maria L. Wei , Michael J. Keiser

Concept-based interpretability for Convolutional Neural Networks (CNNs) aims to align internal model representations with high-level semantic concepts, but existing approaches largely overlook the semantic roles of individual filters and…

Machine Learning · Computer Science 2025-09-24 Xinyu Mu , Hui Dou , Furao Shen , Jian Zhao

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Alexandros Doumanoglou , Stylianos Asteriadis , Dimitrios Zarpalas

Although saliency maps can highlight important regions to explain the reasoning behind image classification in artificial intelligence (AI), the meaning of these regions is left to the user's interpretation. In contrast, conceptbased…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Michihiro Kuroki , Toshihiko Yamasaki

In the area of Intelligent Transportation Systems (ITS), fine-grained vehicle classification systems play an essential role. Recently, the authors have presented a novel vision-based classification approach in which standard end-to-end…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Andreas Caduff , Klaus Zahn , Jonas Hofstetter , Martin Rechsteiner , Patrick Flaig

Deep learning is currently playing a crucial role toward higher levels of artificial intelligence. This paradigm allows neural networks to learn complex and abstract representations, that are progressively obtained by combining simpler…

Audio and Speech Processing · Electrical Eng. & Systems 2019-08-12 Mirco Ravanelli , Yoshua Bengio

Concept-based explanations permit to understand the predictions of a deep neural network (DNN) through the lens of concepts specified by users. Existing methods assume that the examples illustrating a concept are mapped in a fixed direction…

Machine Learning · Computer Science 2022-09-30 Jonathan Crabbé , Mihaela van der Schaar

Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore…

Machine Learning · Computer Science 2018-08-21 Xuan Liu , Xiaoguang Wang , Stan Matwin

We present a novel method of using explainability techniques to design physics-aware neural networks. We demonstrate our approach by developing a convolutional neural network (CNN) for solving an inverse problem for shallow subsurface…

Machine Learning · Computer Science 2023-04-04 Jodie Crocker , Krishna Kumar , Brady R. Cox

Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools,…

Computer Vision and Pattern Recognition · Computer Science 2023-07-12 Yi Liao , Yongsheng Gao , Weichuan Zhang

TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a trained neural network and human-understandable, high-level concepts. Though effective, TCAV…

Artificial Intelligence · Computer Science 2026-05-12 Hasib Aslam , Muhammad Ali Chattha , Muhammad Taha Mukhtar , Muhammad Imran Malik , Andreas Dengel , Sheraz Ahmed

*Concept-based explanations* offer a promising approach for explaining the predictions of deep neural networks in terms of high-level, human-understandable concepts. However, existing methods either do not establish a causal connection…

Machine Learning · Computer Science 2026-05-08 Ronaldo Canizales , Divya Gopinath , Corina Păsăreanu , Ravi Mangal

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…

Computer Vision and Pattern Recognition · Computer Science 2018-02-15 Quanshi Zhang , Ying Nian Wu , Song-Chun Zhu