Siamese Network for RGB-D Salient Object Detection and Beyond

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 44; no. 9; pp. 5541 - 5559
• Main Authors: Fu, Keren, Fan, Deng-Ping, Ji, Ge-Peng, Zhao, Qijun, Shen, Jianbing, Zhu, Ce
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Commonality; Computational modeling; Computer architecture; Feature extraction; Machine learning; Modules; Object detection; Object recognition; RGB-D semantic segmentation; RGB-D SOD; Robustness; Salience; Saliency detection; salient object detection; Semantic segmentation; Semantics; Siamese network; Task analysis; Training
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2021.3073689

Existing RGB-D salient object detection (SOD) models usually treat RGB and depth as independent information and design separate networks for feature extraction from each. Such schemes can easily be constrained by a limited amount of training data or over-reliance on an elaborately designed training process. Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion ( JL-DCF ) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture . In this paper, we propose two effective components: joint learning (JL), and densely cooperative fusion (DCF). The JL module provides robust saliency feature learning by exploiting cross-modal commonality via a Siamese network, while the DCF module is introduced for complementary feature discovery. Comprehensive experiments using five popular metrics show that the designed framework yields a robust RGB-D saliency detector with good generalization. As a result, JL-DCF significantly advances the state-of-the-art models by an average of <inline-formula><tex-math notation="LaTeX">\sim 2.0\%</tex-math> <mml:math><mml:mrow><mml:mo>∼</mml:mo><mml:mn>2</mml:mn><mml:mo>.</mml:mo><mml:mn>0</mml:mn><mml:mo>%</mml:mo></mml:mrow></mml:math><inline-graphic xlink:href="fan-ieq1-3073689.gif"/> </inline-formula> (max F-measure) across seven challenging datasets. In addition, we show that JL-DCF is readily applicable to other related multi-modal detection tasks, including RGB-T (thermal infrared) SOD and video SOD, achieving comparable or even better performance against state-of-the-art methods. We also link JL-DCF to the RGB-D semantic segmentation field, showing its capability of outperforming several semantic segmentation models on the task of RGB-D SOD. These facts further confirm that the proposed framework could offer a potential solution for various applications and provide more insight into the cross-modal complementarity task.