2026-11-03T23:10:53Z https://jmvra.org/oai.php

oai:jmvra.org:JMVRA2610011 2026-10-03 vol4

Saliency-Based Image Classification: A Survey of Methods, Applications, and Open Challenges Mehjabin Saiyad Meet Trivedi Preet Prajapati Jigar Dalvadi saliency maps image classification vision transformers explainable AI saliency-guided training data augmentation token pruning medical imaging Computer Science and IT Saliency, the identification of the image regions that matter most for a visual decision, has evolved from a hand-crafted model of human attention into a general-purpose signal that is used to supervise, augment, compress, and explain modern image classifiers. This survey reviews recent work from 2024 to 2026 on saliency-based image classification and organises it into six categories: (A) saliency-guided data augmentation and mixup, (B) saliency-guided training objectives, (C) saliency-guided input and token selection for efficient inference, (D) saliency-guided feature mining, (E) saliency as explanation and its evaluation, and (F) robustness, trust, and security. For each category we summarise representative methods, the reported empirical gains, and the assumptions on which these gains rest. Across studies, we observe that (i) human or human-like saliency is a useful training signal when labelled data are scarce, (ii) Vision Transformer (ViT) attention has become the dominant saliency source for efficiency-oriented methods, and (iii) the faithfulness of saliency maps remains contested, which limits their use as clinical or safety evidence. We close with a discussion of open problems, including standardised evaluation, the cost of collecting human saliency, and the interaction between saliency and robustness. All quantitative results are reported as stated by the original authors and are not directly comparable across studies. JMVRA Publication 2026-10-03 Text Journal Article info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jmvra.org/viewpaperforall.php?paper=JMVRA2610011 https://jmvra.org/papers/JMVRA2610011.pdf Journal of Modern and Versatile Research Approach; ISSN 2984-8911; Vol. 4; Issue 10; pp. a111-a118 en https://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess Copyright © 2026 The Author(s). Published by JMVRA Publication under the Creative Commons Attribution 4.0 International License (CC BY 4.0).