English
Related papers

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

200 papers

Feature attribution aims to explain the reasoning behind a black-box model's prediction by identifying the impact of each feature on the prediction. Recent work has extended feature attribution to interactions between multiple features.…

Machine Learning · Computer Science 2023-05-17 Yifan Jiang , Shane Steinert-Threlkeld

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine…

Machine Learning · Computer Science 2023-05-24 Poushali Sengupta , Yan Zhang , Sabita Maharjan , Frank Eliassen

Interpretability methods for neural networks are difficult to evaluate because we do not understand the black-box models typically used to test them. This paper proposes a framework in which interpretability methods are evaluated using…

Machine Learning · Computer Science 2020-10-20 Yiding Hao

Various types of saliency methods have been proposed for explaining black-box classification. In image applications, this means highlighting the part of the image that is most relevant for the current decision. Unfortunately, the different…

Computer Vision and Pattern Recognition · Computer Science 2023-11-06 Justus Sagemüller , Olivier Verdier

There is great interest in "saliency methods" (also called "attribution methods"), which give "explanations" for a deep net's decision, by assigning a "score" to each feature/pixel in the input. Their design usually involves…

Machine Learning · Computer Science 2019-06-10 Arushi Gupta , Sanjeev Arora

Conventionally, AI models are thought to trade off explainability for lower accuracy. We develop a training strategy that not only leads to a more explainable AI system for object classification, but as a consequence, suffers no perceptible…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Andrea Zunino , Sarah Adel Bargal , Riccardo Volpi , Mehrnoosh Sameki , Jianming Zhang , Stan Sclaroff , Vittorio Murino , Kate Saenko

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze…

Machine Learning · Computer Science 2024-02-20 Leon Sixt , Maximilian Granz , Tim Landgraf

SmoothGrad and VarGrad are techniques that enhance the empirical quality of standard saliency maps by adding noise to input. However, there were few works that provide a rigorous theoretical interpretation of those methods. We analytically…

Machine Learning · Computer Science 2018-06-11 Junghoon Seo , Jeongyeol Choe , Jamyoung Koo , Seunghyeon Jeon , Beomsu Kim , Taegyun Jeon

We describe an explainable AI saliency map method for use with deep convolutional neural networks (CNN) that is much more efficient than popular fine-resolution gradient methods. It is also quantitatively similar or better in accuracy. Our…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 T. Nathan Mundhenk , Barry Y. Chen , Gerald Friedland

Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it remains unclear for practitioners how to use these…

Machine Learning · Computer Science 2024-01-09 Blair Bilodeau , Natasha Jaques , Pang Wei Koh , Been Kim

Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing…

Estimating music piece difficulty is important for organizing educational music collections. This process could be partially automatized to facilitate the educator's role. Nevertheless, the decisions performed by prevalent deep-learning…

Abstaining classifiers have the option to refrain from providing a prediction for instances that are difficult to classify. The abstention mechanism is designed to trade off the classifier's performance on the accepted data while ensuring a…

Machine Learning · Computer Science 2025-04-15 Daphne Lenders , Andrea Pugnana , Roberto Pellungrini , Toon Calders , Dino Pedreschi , Fosca Giannotti

The rise of AI methods to make predictions and decisions has led to a pressing need for more explainable artificial intelligence (XAI) methods. One common approach for XAI is to produce a post-hoc explanation, explaining why a black box ML…

Artificial Intelligence · Computer Science 2022-12-01 Jinqiang Yu , Alexey Ignatiev , Peter J. Stuckey , Nina Narodytska , Joao Marques-Silva

With the rising necessity of explainable artificial intelligence (XAI), we see an increase in task-dependent XAI methods on varying abstraction levels. XAI techniques on a global level explain model behavior and on a local level explain…

Human-Computer Interaction · Computer Science 2023-07-18 Udo Schlegel , Daniela Oelke , Daniel A. Keim , Mennatallah El-Assady

In various practical situations, matrix factorization methods suffer from poor data quality, such as high data sparsity and low signal-to-noise ratio (SNR). Here, we consider a matrix factorization problem by utilizing auxiliary…

Machine Learning · Statistics 2026-01-06 Zhiwei Wang , Fa Zhang , Cong Zheng , Xianghong Hu , Mingxuan Cai , Can Yang

Feature attribution is a fundamental task in both machine learning and data analysis, which involves determining the contribution of individual features or variables to a model's output. This process helps identify the most important…

Machine Learning · Computer Science 2023-10-26 Jinfeng Zhong , Elsa Negre

In recent years, deep learning has achieved unprecedented success in various computer vision tasks, particularly in object detection. However, the black-box nature and high complexity of deep neural networks pose significant challenges for…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 FatemehSadat Seyedmomeni , Mohammad Ali Keyvanrad

In the field of eXplainable AI (XAI), robust "blackbox" algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require…

Machine Learning · Computer Science 2021-11-25 Shaw-Hwa Lo , Yiqiao Yin

Post-hoc explainable AI (XAI) methods typically produce deterministic attribution maps, whereas Bayesian neural networks (BNNs) induce a distribution over explanations. Capturing the variability of this distribution is important for…

Machine Learning · Computer Science 2026-05-21 Yinsong Chen , Samson S. Yu , Zhong Li , Chee Peng Lim