Lightweight RGB-D Salient Object Detection From a Speed-Accuracy Tradeoff Perspective
IEEE Transactions on Image Processing · 2025 · 34 · 2529-2543
DOI: 10.1109/tip.2025.3560488 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Songsong Duan und 3 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Projects of Shaanxi Province, Shaanxi Outstanding Youth Science Fund Project.
Abstract (Originalsprache)
Current RGB-D methods usually leverage large-scale backbones to improve accuracy but sacrifice efficiency. Meanwhile, several existing lightweight methods are difficult to achieve high-precision performance. To balance the efficiency and performance, we propose a Speed-Accuracy Tradeoff Network (SATNet) for Lightweight RGB-D SOD from three fundamental perspectives: depth quality, modality fusion, and feature representation. Concerning depth quality, we introduce the Depth Anything Model to generate high-quality depth maps,which effectively alleviates the multi-modal gaps in the current datasets. For modality fusion, we propose a Decoupled Attention Module (DAM) to explore the consistency within and between modalities. Here, the multi-modal features are decoupled into dual-view feature vectors to project discriminable information of feature maps. For feature representation, we develop a Dual Information Representation Module (DIRM) with a bi-directional inverted framework to enlarge the limited feature space generated by the lightweight backbones. DIRM models texture features and saliency features to enrich feature space, and employ two-way prediction heads to optimal its parameters through a bi-directional backpropagation. Finally, we design a Dual Feature Aggregation Module (DFAM) in the decoder to aggregate texture and saliency features. Extensive experiments on five public RGB-D SOD datasets indicate that the proposed SATNet excels state-of-the-art (SOTA) CNN-based heavyweight models and achieves a lightweight framework with 5.2 M parameters and 415 FPS. The code is available at https://github.com/duan-song/SATNet.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Projects of Shaanxi Province
- Shaanxi Outstanding Youth Science Fund Project
- Shaanxi Province Core Technology Research and Development Project
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Duan, S., Yang, X., Wang, N., & Gao, X. (2025). Lightweight RGB-D Salient Object Detection From a Speed-Accuracy Tradeoff Perspective. IEEE Transactions on Image Processing, 34, 2529-2543. https://doi.org/10.1109/tip.2025.3560488
Vancouver
Duan S, Yang X, Wang N, Gao X. Lightweight RGB-D Salient Object Detection From a Speed-Accuracy Tradeoff Perspective. IEEE Transactions on Image Processing. 2025;34:2529-2543. doi:10.1109/tip.2025.3560488
BibTeX
@article{Duan2025,
author = {Duan, Songsong and Yang, Xi and Wang, Nannan and Gao, Xinbo},
title = {Lightweight RGB-D Salient Object Detection From a Speed-Accuracy Tradeoff Perspective},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {2529--2543},
doi = {10.1109/tip.2025.3560488}
}
EUVIMED