English
Related papers

Related papers: One Wave To Explain Them All: A Unifying Perspecti…

200 papers

Deep Neural Networks (DNNs) have shown remarkable success in various computer vision tasks. However, their black-box nature often leads to difficulty in interpreting their decisions, creating an unfilled need for methods to explain the…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Daniel Siegismund , Mario Wieser , Stephan Heyse , Stephan Steigele

Segmentation, a useful/powerful technique in pattern recognition, is the process of identifying object outlines within images. There are a number of efficient algorithms for segmentation in Euclidean space that depend on the variational…

Computer Vision and Pattern Recognition · Computer Science 2019-11-12 Xiaohao Cai , Christopher G. R. Wallis , Jennifer Y. H. Chan , Jason D. McEwen

Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a…

Machine Learning · Computer Science 2019-01-30 Umang Bhatt , Pradeep Ravikumar , Jose M. F. Moura

Deep learning models extract, before a final classification layer, features or patterns which are key for their unprecedented advantageous performance. However, the process of complex nonlinear feature extraction is not well understood, a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-18 Roozbeh Yousefzadeh , Furong Huang

Feature attribution methods, such as SHAP and LIME, explain machine learning model predictions by quantifying the influence of each input component. When applying feature attributions to explain language models, a basic question is defining…

Human-Computer Interaction · Computer Science 2025-09-26 Alan Boyle , Furui Cheng , Vilém Zouhar , Mennatallah El-Assady

Explainable AI (XAI) promises to provide insight into machine learning models' decision processes, where one goal is to identify failures such as shortcut learning. This promise relies on the field's assumption that input features marked as…

Machine Learning · Computer Science 2026-02-19 Benedict Clark , Marta Oliveira , Rick Wilming , Stefan Haufe

Attribution methods calculate attributions that visually explain the predictions of deep neural networks (DNNs) by highlighting important parts of the input features. In particular, gradient-based attribution (GBA) methods are widely used…

Machine Learning · Computer Science 2021-02-16 Jae-Hong Lee , Joon-Hyuk Chang

Deep unfolding networks have gained increasing attention in the field of compressed sensing (CS) owing to their theoretical interpretability and superior reconstruction performance. However, most existing deep unfolding methods often face…

Image and Video Processing · Electrical Eng. & Systems 2025-04-17 Kai Han , Jin Wang , Yunhui Shi , Hanqin Cai , Nam Ling , Baocai Yin

Machine learning transparency calls for interpretable explanations of how inputs relate to predictions. Feature attribution is a way to analyze the impact of features on predictions. Feature interactions are the contextual dependence…

Machine Learning · Statistics 2020-06-22 Michael Tsang , Sirisha Rambhatla , Yan Liu

Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the…

Machine Learning · Computer Science 2025-06-10 Mateusz Gajewski , Mikołaj Morzy , Adam Karczmarz , Piotr Sankowski

Class attribution maps (CAMs) provide local explanations for the decisions of convolutional neural networks. While widely used in practice, the evaluation of CAMs remains challenging due to the lack of ground-truth explanations, making it…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Luca Domeniconi , Alessandra Stramiglio , Michele Lombardi , Samuele Salti

Deep neural networks are very successful on many vision tasks, but hard to interpret due to their black box nature. To overcome this, various post-hoc attribution methods have been proposed to identify image regions most influential to the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Sukrut Rao , Moritz Böhle , Bernt Schiele

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate…

Machine Learning · Computer Science 2025-05-13 Zhiyu Zhu , Jiayu Zhang , Zhibo Jin , Fang Chen , Jianlong Zhou

Feature attribution is essential for interpreting deep learning models, particularly in time-series domains such as healthcare, biometrics, and human-AI interaction. However, standard attribution methods, such as Integrated Gradients or…

Machine Learning · Computer Science 2025-09-25 Benedikt W. Hosp

Machine and deep learning have grown in popularity and use in biological research over the last decade but still present challenges in interpretability of the fitted model. The development and use of metrics to determine features driving…

Machine Learning · Statistics 2025-07-31 Daniel Claborne , Javier Flores , Samantha Erwin , Luke Durell , Rachel Richardson , Ruby Fore , Lisa Bramer

Pixel intensity is a widely used feature for clustering and segmentation algorithms, the resulting segmentation using only intensity values might suffer from noises and lack of spatial context information. Wavelet transform is often used…

Image and Video Processing · Electrical Eng. & Systems 2019-07-09 Junyu Chen , Eric C. Frey

Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribution remains a challenge. There are several views through…

Machine Learning · Computer Science 2024-11-26 Yawei Li , Yang Zhang , Kenji Kawaguchi , Ashkan Khakzar , Bernd Bischl , Mina Rezaei

Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primarily focus on acquiring informative fusion images at the visual…

Computer Vision and Pattern Recognition · Computer Science 2025-02-04 Haowen Bai , Zixiang Zhao , Jiangshe Zhang , Baisong Jiang , Lilun Deng , Yukun Cui , Shuang Xu , Chunxia Zhang

We present a method for neural network interpretability by combining feature attribution with counterfactual explanations to generate attribution maps that highlight the most discriminative features between pairs of classes. We show that…

Machine Learning · Computer Science 2021-09-29 Nils Eckstein , Alexander S. Bates , Gregory S. X. E. Jefferis , Jan Funke

While a lot of research in explainable AI focuses on producing effective explanations, less work is devoted to the question of how people understand and interpret the explanation. In this work, we focus on this question through a study of…

Computation and Language · Computer Science 2022-06-20 Hendrik Schuff , Alon Jacovi , Heike Adel , Yoav Goldberg , Ngoc Thang Vu