English
Related papers

Related papers: Saliency strikes back: How filtering out high freq…

200 papers

This study investigates the impact of machine learning models on the generation of counterfactual explanations by conducting a benchmark evaluation over three different types of models: a decision tree (fully transparent, interpretable,…

Machine Learning · Computer Science 2024-11-11 Catarina Moreira , Yu-Liang Chou , Chihcheng Hsieh , Chun Ouyang , João Madeiras Pereira , Joaquim Jorge

Detecting out-of-distribution (OOD) examples is crucial to guarantee the reliability and safety of deep neural networks in real-world settings. In this paper, we offer an innovative perspective on quantifying the disparities between…

Machine Learning · Computer Science 2024-01-17 Jinggang Chen , Junjie Li , Xiaoyang Qu , Jianzong Wang , Jiguang Wan , Jing Xiao

Adapting pretrained diffusion models to downstream objectives such as inverse problems often requires expensive test-time guidance or optimization. We propose a principled framework for generating high-quality reward-aligned samples at…

Machine Learning · Computer Science 2026-05-22 Kushagra Pandey , Farrin Marouf Sofian , Jan Niklas Groeneveld , Felix Draxler , Stephan Mandt

Integrated Gradients (IG) is a widely used attribution method in explainable AI, particularly in computer vision applications where reliable feature attribution is essential. A key limitation of IG is its sensitivity to the choice of…

Machine Learning · Statistics 2025-11-21 Kien Tran Duc Tuan , Tam Nguyen Trong , Son Nguyen Hoang , Khoat Than , Anh Nguyen Duc

Feature attribution methods identify which features of an input most influence a model's output. Most widely-used feature attribution methods (such as SHAP, LIME, and Grad-CAM) are "class-dependent" methods in that they generate a feature…

Machine Learning · Computer Science 2023-02-28 Neil Jethani , Adriel Saporta , Rajesh Ranganath

Rapid development of advanced modelling techniques gives an opportunity to develop tools that are more and more accurate. However as usually, everything comes with a price and in this case, the price to pay is to loose interpretability of a…

We examined whether embedding human attention knowledge into saliency-based explainable AI (XAI) methods for computer vision models could enhance their plausibility and faithfulness. We first developed new gradient-based XAI methods for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-08 Guoyang Liu , Jindi Zhang , Antoni B. Chan , Janet H. Hsiao

Generative AI has redefined artificial intelligence, enabling the creation of innovative content and customized solutions that drive business practices into a new era of efficiency and creativity. In this paper, we focus on diffusion…

Machine Learning · Computer Science 2024-03-21 Zihao Li , Hui Yuan , Kaixuan Huang , Chengzhuo Ni , Yinyu Ye , Minshuo Chen , Mengdi Wang

We propose a fast and simple explainable AI (XAI) method for point cloud data. It computes pointwise importance with respect to a trained network downstream task. This allows better understanding of the network properties, which is…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Meir Yossef Levi , Guy Gilboa

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability. One flourishing approach is through counterfactual explanations, which provide…

Artificial Intelligence · Computer Science 2023-06-02 Vy Vo , Trung Le , Van Nguyen , He Zhao , Edwin Bonilla , Gholamreza Haffari , Dinh Phung

Uncertainty is a key feature of any machine learning model and is particularly important in neural networks, which tend to be overconfident. This overconfidence is worrying under distribution shifts, where the model performance silently…

Machine Learning · Computer Science 2024-03-18 Arthur Thuy , Dries F. Benoit

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all features in a dataset…

Artificial Intelligence · Computer Science 2022-03-25 Veera Raghava Reddy Kovvuri , Siyuan Liu , Monika Seisenberger , Berndt Müller , Xiuyi Fan

We study the problem of attributing the prediction of a deep network to its input features, a problem previously studied by several other works. We identify two fundamental axioms---Sensitivity and Implementation Invariance that attribution…

Machine Learning · Computer Science 2017-06-14 Mukund Sundararajan , Ankur Taly , Qiqi Yan

Gradient-based saliency maps are widely used to explain deep neural network decisions. However, as models become deeper and more black-box, such as in closed-source APIs like ChatGPT, computing gradients become challenging, hindering…

Computer Vision and Pattern Recognition · Computer Science 2024-07-03 Zeliang Zhang , Mingqian Feng , Jinyang Jiang , Rongyi Zhu , Yijie Peng , Chenliang Xu

In machine learning algorithm design, there exists a trade-off between the interpretability and performance of the algorithm. In general, algorithms which are simpler and easier for humans to comprehend tend to show worse performance than…

Machine Learning · Computer Science 2024-07-15 Eric M. Vernon , Naoki Masuyama , Yusuke Nojima

Prediction systems are successfully deployed in applications ranging from disease diagnosis, to predicting credit worthiness, to image recognition. Even when the overall accuracy is high, these systems may exhibit systematic biases that…

Machine Learning · Computer Science 2018-08-30 Michael P. Kim , Amirata Ghorbani , James Zou

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres Figueroa , Hanwei Zhang , Ronan Sicre , Yannis Avrithis , Stephane Ayache

Linear Programs (LPs) have been one of the building blocks in machine learning and have championed recent strides in differentiable optimizers for learning systems. While there exist solvers for even high-dimensional LPs, understanding said…

Machine Learning · Computer Science 2022-06-16 Florian Peter Busch , Matej Zečević , Kristian Kersting , Devendra Singh Dhami

Feedback in creativity support tools can help crowdworkers to improve their ideations. However, current feedback methods require human assessment from facilitators or peers. This is not scalable to large crowds. We propose Interpretable…

Human-Computer Interaction · Computer Science 2022-03-29 Yunlong Wang , Priyadarshini Venkatesh , Brian Y. Lim

A popular approach to unveiling the black box of neural NLP models is to leverage saliency methods, which assign scalar importance scores to each input component. A common practice for evaluating whether an interpretability method is…

Computation and Language · Computer Science 2023-05-12 Josip Jukić , Martin Tutek , Jan Šnajder