English
Related papers

Related papers: Baseline Computation for Attribution Methods Based…

200 papers

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

There has been a surge in Explainable-AI (XAI) methods that provide insights into the workings of Deep Neural Network (DNN) models. Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features…

Machine Learning · Computer Science 2023-02-23 Ashwin Bhat , Arijit Raychowdhury

Explaining deep learning models in a way that humans can easily understand is essential for responsible artificial intelligence applications. Attribution methods constitute an important area of explainable deep learning. The attribution…

Computer Vision and Pattern Recognition · Computer Science 2025-01-22 Michal Byra , Henrik Skibbe

Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Jiarui Duan , Haoling Li , Haofei Zhang , Hao Jiang , Mengqi Xue , Li Sun , Mingli Song , Jie Song

Methods based on class activation maps (CAM) provide a simple mechanism to interpret predictions of convolutional neural networks by using linear combinations of feature maps as saliency maps. By contrast, masking-based methods optimize a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Hanwei Zhang , Felipe Torres , Ronan Sicre , Yannis Avrithis , Stephane Ayache

Attribution methods have been shown as promising approaches for identifying key features that led to learned model predictions. While most existing attribution methods rely on a baseline input for performing feature perturbations, limited…

Machine Learning · Computer Science 2021-06-24 Sheng-Min Shih , Pin-Ju Tien , Zohar Karnin

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

Data attribution for generative models seeks to quantify the influence of individual training examples on model outputs. Existing methods for diffusion models typically require access to model gradients or retraining, limiting their…

Machine Learning · Computer Science 2025-10-17 Yutian Zhao , Chao Du , Xiaosen Zheng , Tianyu Pang , Min Lin

Attribution methods in explainable AI rely on upsampling techniques that were designed for natural images, not saliency maps. Standard bilinear and bicubic interpolation systematically corrupts attribution signals through aliasing, ringing,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Vincenzo Buono , Peyman Sheikholharam Mashhadi , Mahmoud Rahat , Prayag Tiwari , Stefan Byttner

We propose a conditional stochastic interpolation (CSI) method for learning conditional distributions. CSI is based on estimating probability flow equations or stochastic differential equations that transport a reference distribution to the…

Machine Learning · Statistics 2025-08-26 Ding Huang , Jian Huang , Ting Li , Guohao Shen

Interleaving is an online evaluation approach for information retrieval systems that compares the effectiveness of ranking functions in interpreting the users' implicit feedback. Previous work such as Hofmann et al (2011) has evaluated the…

Information Retrieval · Computer Science 2023-03-20 Alessandro Benedetti , Anna Ruggero

Generative models based on normalizing flows are very successful in modeling complex data distributions using simpler ones. However, straightforward linear interpolations show unexpected side effects, as interpolation paths lie outside the…

Machine Learning · Statistics 2025-04-09 Samuel G. Fadel , Sebastian Mair , Ricardo da S. Torres , Ulf Brefeld

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…

Machine Learning · Computer Science 2019-11-06 Mengjiao Yang , Been Kim

Graphs are complex objects that do not lend themselves easily to typical learning tasks. Recently, a range of approaches based on graph kernels or graph neural networks have been developed for graph classification and for representation…

Machine Learning · Computer Science 2022-05-19 Chen Cai , Yusu Wang

We propose deep parameter interpolation (DPI), a general-purpose method for transforming an existing deep neural network architecture into one that accepts an additional scalar input. Recent deep generative models, including diffusion…

Image and Video Processing · Electrical Eng. & Systems 2025-11-27 Chicago Y. Park , Michael T. McCann , Cristina Garcia-Cardona , Brendt Wohlberg , Ulugbek S. Kamilov

We extend previous mean-field approaches for non-equilibrium neural network models to estimate correlations in the system. This offers a powerful tool for approximating the system dynamics as well as a fast method to infer network…

Disordered Systems and Neural Networks · Physics 2022-01-27 Ángel Poc-López , Miguel Aguilera

Saliency methods can aid understanding of deep neural networks. Recent years have witnessed many improvements to saliency methods, as well as new ways for evaluating them. In this paper, we 1) present a novel region-based attribution…

Computer Vision and Pattern Recognition · Computer Science 2019-08-22 Andrei Kapishnikov , Tolga Bolukbasi , Fernanda Viégas , Michael Terry

We consider an investment process that includes a number of features, each of which can be active or inactive. Our goal is to attribute or decompose an achieved performance to each of these features, plus a baseline value. There are many…

Computational Finance · Quantitative Finance 2021-02-12 Nicholas Moehle , Stephen Boyd , Andrew Ang

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level explainability, however for many clinical applications a deeper,…

Image and Video Processing · Electrical Eng. & Systems 2023-03-16 Ario Sadafi , Oleksandra Adonkina , Ashkan Khakzar , Peter Lienemann , Rudolf Matthias Hehr , Daniel Rueckert , Nassir Navab , Carsten Marr