paper-with-me

홈 › Papers

Saliency Maps Give a False Sense of Explanability to Image Classifiers: An Empirical Evaluation across Methods and Metrics

2024-12-03 · ACML 2024 12 · Hanwei Zhang, Felipe Torres Figueroa, Holger Hermanns

The interpretability of deep neural networks (DNNs) has emerged as a crucial area of research, particularly in image classification tasks where decisions often lack transparency. Saliency maps have been widely used as a tool to decode the inner workings of these networks by highlighting regions of input images deemed most influential in the classification process. However, recent studies have revealed significant limitations and inconsistencies in the utility of saliency maps as explanations. This paper aims to systematically assess the shortcomings of saliency maps and explore alternative approaches to achieve more reliable and interpretable explanations for image classification models. We carry out a series of experiments to show that 1) the existing evaluation does not provide a fair nor meaningful comparison to the existing saliency maps; these evaluations have their implicit assumption and are not differentiable; 2) the saliency maps do not provide enough information on explaining the accuracy of network, the relationship between classes and the modification of the images.

📄 PDF Abstract BibTeX

Code (1)

ftorres11/saliencysense pytorch

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Instance-level quantitative saliency in multiple sclerosis lesion segmentation

2024-06-13 · Federico Spagnolo, Nataliia Molchanova, Roger Schaer, Meritxell Bach Cuadra 외

In recent years, explainable methods for artificial intelligence (XAI) have tried to reveal and describe models' decision mechanisms in the case of classification tasks. However, XAI for semantic segmentation and in part…

Date UnderstandingLesion SegmentationSegmentationSemantic Segmentation

What do different evaluation metrics tell us about saliency models?

2016-04-12 · Zoya Bylinskii, Tilke Judd, Aude Oliva, Antonio Torralba 외

How best to evaluate a saliency model's ability to predict where humans look in images is an open research question. The choice of evaluation metric depends on how saliency is defined and how the ground truth is represen…

Divisive Decisions: Improving Salience-Based Training for Generalization in Binary Classification Tasks

2025-07-22 · Jacob Piland, Chris Sweet, Adam Czajka arxiv

Existing saliency-guided training approaches improve model generalization by incorporating a loss term that compares the model's class activation map (CAM) for a sample's true-class ({\it i.e.}, correct-label class) agai…

Binary ClassificationFace Detection

Canonical Saliency Maps: Decoding Deep Face Models

2021-05-04 · Thrupthi Ann John, Vineeth N Balasubramanian, C V Jawahar

As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may hav…

Face ModelObject Recognition

eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks

2025-03-13 · Stephen Wormald, David Koblah, Matheus Kunzler Maldaner, Domenic Forte 외

Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity …