English
Related papers

Related papers: The (Un)reliability of saliency methods

200 papers

Saliency methods are widely used to interpret neural network predictions, but different variants of saliency methods often disagree even on the interpretations of the same prediction made by the same model. In these cases, how do we…

Computation and Language · Computer Science 2021-04-14 Shuoyang Ding , Philipp Koehn

Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2020-11-09 Julius Adebayo , Justin Gilmer , Michael Muelly , Ian Goodfellow , Moritz Hardt , Been Kim

Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Roman Levin , Manli Shu , Eitan Borgnia , Furong Huang , Micah Goldblum , Tom Goldstein

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Aya Abdelsalam Ismail , Héctor Corrada Bravo , Soheil Feizi

The correct interpretation of convolutional models is a hard problem for time series data. While saliency methods promise visual validation of predictions for image and language processing, they fall short when applied to time series. These…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Christoffer Loeffler , Wei-Cheng Lai , Bjoern Eskofier , Dario Zanca , Lukas Schmidt , Christopher Mutschler

With their increase in performance, neural network architectures also become more complex, necessitating explainability. Therefore, many new and improved methods are currently emerging, which often generate so-called saliency maps in order…

Machine Learning · Computer Science 2024-12-24 Leonid Schwenke , Martin Atzmueller

Deep Neural Networks are powerful tools to understand complex patterns and making decisions. However, their black-box nature impedes a complete understanding of their inner workings. While online saliency-guided training methods try to…

Computer Vision and Pattern Recognition · Computer Science 2023-06-30 Ali Karkehabadi

Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recent work on explaining deep models has introduced approaches…

Computation and Language · Computer Science 2019-05-21 Reza Ghaeini , Xiaoli Z. Fern , Hamed Shahbazi , Prasad Tadepalli

Saliency methods compute heat maps that highlight portions of an input that were most {\em important} for the label assigned to it by a deep net. Evaluations of saliency methods convert this heat map into a new {\em masked input} by…

Machine Learning · Statistics 2022-11-08 Arushi Gupta , Nikunj Saunshi , Dingli Yu , Kaifeng Lyu , Sanjeev Arora

Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.…

Machine Learning · Computer Science 2021-06-15 Yang Lu , Wenbo Guo , Xinyu Xing , William Stafford Noble

We address the need to generate faithful explanations of "black box" Deep Learning models. Several tests have been proposed to determine aspects of faithfulness of explanation methods, but they lack cross-domain applicability and a rigorous…

Machine Learning · Computer Science 2023-06-27 Harshinee Sriram , Cristina Conati

Saliency methods seek to explain the predictions of a model by producing an importance map across each input sample. A popular class of such methods is based on backpropagating a signal and analyzing the resulting gradient. Despite much…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Sylvestre-Alvise Rebuffi , Ruth Fong , Xu Ji , Andrea Vedaldi

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Aidan Boyd , Mohamed Trabelsi , Huseyin Uzunalioglu , Dan Kushnir

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Naveed Akhtar , Mohammad A. A. K. Jalwana

The performance of convolutional neural networks has continued to improve over the last decade. At the same time, as model complexity grows, it becomes increasingly more difficult to explain model decisions. Such explanations may be of…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Colton Crum , Patrick Tinsley , Aidan Boyd , Jacob Piland , Christopher Sweet , Timothy Kelley , Kevin Bowyer , Adam Czajka

The classification decisions of neural networks can be misled by small imperceptible perturbations. This work aims to explain the misled classifications using saliency methods. The idea behind saliency methods is to explain the…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Jindong Gu , Volker Tresp

Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-29 Ali Karkehabadi , Jamshid Hassanpour , Houman Homayoun , Avesta Sasan

Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In…

Machine Learning · Computer Science 2020-10-28 Aya Abdelsalam Ismail , Mohamed Gunady , Héctor Corrada Bravo , Soheil Feizi

The opacity of deep learning models constrains their debugging and improvement. Augmenting deep models with saliency-based strategies, such as attention, has been claimed to help get a better understanding of the decision-making process of…

Computer Vision and Pattern Recognition · Computer Science 2022-11-16 Matteo Rizzo , Cristina Conati , Daesik Jang , Hui Hu

A fundamental bottleneck in utilising complex machine learning systems for critical applications has been not knowing why they do and what they do, thus preventing the development of any crucial safety protocols. To date, no method exist…

Machine Learning · Computer Science 2023-01-18 Jan Rosenzweig , Zoran Cvetkovic , Ivana Rosenzweig
‹ Prev 1 2 3 10 Next ›