Abstract | ||
---|---|---|
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 (
<italic/>
JL-DCF
<italic/>
) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the
<i>Siamese architecture</i>
. 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></inline-formula>
(max F-measure) across seven challenging datasets. In addition, we show that
<italic/>
JL-DCF
<italic/>
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
<italic/>
JL-DCF
<italic/>
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. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TPAMI.2021.3073689 | IEEE Transactions on Pattern Analysis and Machine Intelligence |
Keywords | DocType | Volume |
Siamese network,RGB-D SOD,saliency detection,salient object detection,RGB-D semantic segmentation | Journal | 44 |
Issue | ISSN | Citations |
9 | 0162-8828 | 14 |
PageRank | References | Authors |
0.47 | 92 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Keren Fu | 1 | 295 | 26.25 |
Deng-Ping Fan | 2 | 195 | 15.31 |
Ge-Peng Ji | 3 | 92 | 6.23 |
Qijun Zhao | 4 | 419 | 38.37 |
Jianbing Shen | 5 | 584 | 33.35 |
Ce Zhu | 6 | 1473 | 117.79 |