English
Related papers

Related papers: Concept Activation Regions: A Generalized Framewor…

200 papers

Convolutional neural networks (CNNs) are increasingly being used in critical systems, where robustness and alignment are crucial. In this context, the field of explainable artificial intelligence has proposed the generation of high-level…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Andres Felipe Posada-Moreno , Nikita Surya , Sebastian Trimpe

Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by statistical instability. We analyze the stochastic nature of CAVs and the Testing with…

Machine Learning · Statistics 2026-05-18 Ekkehard Schnoor , Jawher Said , Malik Tiomoko , Wojciech Samek , Alexander Jung

A major challenge in Explainable AI is in correctly interpreting activations of hidden neurons: accurate interpretations would provide insights into the question of what a deep learning system has internally detected as relevant on the…

Machine Learning · Computer Science 2023-08-10 Abhilekha Dalal , Md Kamruzzaman Sarker , Adrita Barua , Eugene Vasserman , Pascal Hitzler

Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…

Machine Learning · Statistics 2017-12-13 Yoshihiro Nagano , Ryo Karakida , Masato Okada

Interpreting and understanding the predictions made by deep learning models poses a formidable challenge due to their inherently opaque nature. Many previous efforts aimed at explaining these predictions rely on input features,…

Computation and Language · Computer Science 2024-10-10 Xuemin Yu , Fahim Dalvi , Nadir Durrani , Marzia Nouri , Hassan Sajjad

Self-driving cars increasingly rely on deep neural networks to achieve human-like driving. The opacity of such black-box planners makes it challenging for the human behind the wheel to accurately anticipate when they will fail, with…

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To…

Computation and Language · Computer Science 2019-04-03 Robert Schwarzenberg , Lisa Raithel , David Harbecke

In this work, we propose CLass-Enhanced Attentive Response (CLEAR): an approach to visualize and understand the decisions made by deep neural networks (DNNs) given a specific input. CLEAR facilitates the visualization of attentive regions…

Computer Vision and Pattern Recognition · Computer Science 2017-05-22 Devinder Kumar , Alexander Wong , Graham W. Taylor

Deep Neural Networks (DNNs) are often considered black boxes due to their opaque decision-making processes. To reduce their opacity Concept Models (CMs), such as Concept Bottleneck Models (CBMs), were introduced to predict human-defined…

Human-Computer Interaction · Computer Science 2025-12-02 Jack Furby , Dan Cunnington , Dave Braines , Alun Preece

Concept probing has recently gained popularity as a way for humans to peek into what is encoded within artificial neural networks. In concept probing, additional classifiers are trained to map the internal representations of a model into…

Machine Learning · Computer Science 2025-07-28 Manuel de Sousa Ribeiro , Afonso Leote , João Leite

Deep learning models often function as black boxes, providing no straightforward reasoning for their predictions. This is particularly true for computer vision models, which process tensors of pixel values to generate outcomes in tasks such…

Computer Vision and Pattern Recognition · Computer Science 2024-10-02 Sachin Karmani , Thanushon Sivakaran , Gaurav Prasad , Mehmet Ali , Wenbo Yang , Sheyang Tang

Deep learning methods for classifying medical images have demonstrated impressive accuracy in a wide range of tasks but often these models are hard to interpret, limiting their applicability in clinical practice. In this work we introduce a…

Image and Video Processing · Electrical Eng. & Systems 2019-08-13 James R. Clough , Ilkay Oksuz , Esther Puyol-Anton , Bram Ruijsink , Andrew P. King , Julia A. Schnabel

Ontological commitment, i.e., used concepts, relations, and assumptions, are a corner stone of qualitative reasoning (QR) models. The state-of-the-art for processing raw inputs, though, are deep neural networks (DNNs), nowadays often based…

Computer Vision and Pattern Recognition · Computer Science 2024-09-26 Mert Keser , Gesina Schwalbe , Niki Amini-Naieni , Matthias Rottmann , Alois Knoll

Fetal standard scan plane detection during 2-D mid-pregnancy examinations is a highly complex task, which requires extensive medical knowledge and years of training. Although deep neural networks (DNN) can assist inexperienced operators in…

Machine Learning · Computer Science 2026-03-09 Yingni Wanga , Yunxiao Liua , Licong Dongc , Xuzhou Wua , Huabin Zhangb , Qiongyu Yed , Desheng Sunc , Xiaobo Zhoue , Kehong Yuan

Fault detection for Deep Neural Networks (DNNs) has received increasing attention in recent years. While more advanced hybrid approaches have been proposed to combine multiple sources of information and outperform earlier techniques, they…

Machine Learning · Computer Science 2026-05-26 Amin Abbasishahkoo , Mahboubeh Dadkhah , Lionel Briand

Safety-critical applications require transparency in artificial intelligence (AI) components, but widely used convolutional neural networks (CNNs) widely used for perception tasks lack inherent interpretability. Hence, insights into what…

Computer Vision and Pattern Recognition · Computer Science 2023-06-28 Georgii Mikriukov , Gesina Schwalbe , Christian Hellert , Korinna Bade

One of the current key challenges in Explainable AI is in correctly interpreting activations of hidden neurons. It seems evident that accurate interpretations thereof would provide insights into the question what a deep learning system has…

Machine Learning · Computer Science 2023-01-24 Abhilekha Dalal , Md Kamruzzaman Sarker , Adrita Barua , Pascal Hitzler

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class…

Interpreting the inner workings of deep learning models is crucial for establishing trust and ensuring model safety. Concept-based explanations have emerged as a superior approach that is more interpretable than feature attribution…

Machine Learning · Computer Science 2023-07-17 Mara Graziani , Laura O' Mahony , An-Phi Nguyen , Henning Müller , Vincent Andrearczyk

Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of…

Machine Learning · Computer Science 2022-01-06 Adriano Lucieri , Muhammad Naseer Bajwa , Andreas Dengel , Sheraz Ahmed