Deep Learning Survey on Saliency Detection: Encoders to Decoder Refinements

DOI

10.2991/978-94-6239-789-7_15How to use a DOI?

Keywords

Image Saliency Detection; Encoder-Decoder Networks; CNN Architectures; Transformer Integration; Visual Attention; Evaluation Metrics; Hybrid Models

Abstract

This paper presents a thorough examination of the encoderdecoder architecture for detection of salient image regions, a key objective in the area of computer vision (CV) where it is necessary to locate and evaluate the primary visible features within an image. Beginning with a description of how design has progressed over the years from about 2010, the paper looks back to when CNN-type neural networks were initially developed and have been subsequently transformed into more sophisticated networks through the use of transformer technologies. Additionally, some important benchmarks and measures are included to allow the reader to consider the effectiveness of a particular network at accurately classifying images. Finally, discussion is provided regarding the current problems that exist within the field, such as the need for fast and effective algorithms and accurate boundary detection, as well as potential future research directions, including the development of mixed and composite architectures and new and improved methods of implementing foundation models.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gaurav Aggarwal
AU  - Ankush Joshi
PY  - 2026
DA  - 2026/10/08
TI  - Deep Learning Survey on Saliency Detection: Encoders to Decoder Refinements
BT  - Proceedings of theInternational Conference on Innovation and Practices in Artificial Intelligence (ICIPAI 2026)
PB  - Atlantis Press
SP  - 198
EP  - 210
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-789-7_15
DO  - 10.2991/978-94-6239-789-7_15
ID  - Aggarwal2026
ER  -