RCNet: Related Context-Driven Network with Hierarchical Attention for Salient Object Detection
Article
Xia, Chenxing, Sun, Yanguang, Li, Kuan-Ching, Ge, Bin, Zhang, Hanling, Jiang, Bo and Zhang, Ji. 2024. "RCNet: Related Context-Driven Network with Hierarchical Attention for Salient Object Detection." Expert Systems with Applications. 237 (Part A). https://doi.org/10.1016/j.eswa.2023.121441
| Article Title | RCNet: Related Context-Driven Network with Hierarchical Attention for Salient Object Detection |
|---|---|
| ERA Journal ID | 17852 |
| Article Category | Article |
| Authors | Xia, Chenxing, Sun, Yanguang, Li, Kuan-Ching, Ge, Bin, Zhang, Hanling, Jiang, Bo and Zhang, Ji |
| Journal Title | Expert Systems with Applications |
| Journal Citation | 237 (Part A) |
| Article Number | 121441 |
| Number of Pages | 14 |
| Year | 2024 |
| Publisher | Elsevier |
| Place of Publication | United Kingdom |
| ISSN | 0957-4174 |
| 1873-6793 | |
| Digital Object Identifier (DOI) | https://doi.org/10.1016/j.eswa.2023.121441 |
| Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0957417423019437 |
| Abstract | Recent progress in salient object detection (SOD) mainly depends on dilated convolution with different receptive fields to capture contextual information for multi-scale learning. Intuitively, contextual information in different scales is conducive to understanding the image content, and thus can help us identify and locate salient objects in real-world scenes. However, the sparsity inside the dilated convolution kernel may cause the problem of local information loss, limiting the predictive accuracy of the model. In addition, the inequality of feature channels should also be considered, and they often feature different deviations for salient objects or background noises. Although some channel attention mechanisms have been proposed in SOD, their ability to capture global information is limited, and the problem of high complexity is still a great challenge. To alleviate the abovementioned problems, we propose a Related Context-Driven Network (RCNet) with Hierarchical Attention for Salient Object Detection, consisting of a cascaded multi-scale context exploration (CMCE) module and a hierarchical feature aggregation (HFA) module. The CMCE module is to capture multi-scale contextual information through using multi-receptive-field dilated convolutions in a diamond hierarchical structure, where a feature reconstruction operation is deployed to improve the correlation of features, effectively avoiding the gridding problems and local information loss. Meanwhile, the HFA module adaptively interacts with the complementary information of the multi-level features to further capture the important information from within the feature channel by a multi-source hybrid channel attention (MHCA) mechanism to generate powerful and robust feature representations. Extensive experiments on six benchmark datasets demonstrate that the proposed RCNet method consistently outperforms 20 existing the state-of-the-art SOD methods in terms of accuracy, generalization capacity and robustness. |
| Keywords | Attention mechanism; Multi-scale contextual information; Salient object detection |
| Contains Sensitive Content | Does not contain sensitive content |
| ANZSRC Field of Research 2020 | 460999. Information systems not elsewhere classified |
| Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
| Byline Affiliations | Anhui University of Science and Technology, China |
| Nanjing University of Information Science and Technology, China | |
| Providence University, Taiwan | |
| Hunan University, China | |
| Anhui University, China | |
| School of Mathematics, Physics and Computing |
Permalink -
https://research.usq.edu.au/item/z5vz3/rcnet-related-context-driven-network-with-hierarchical-attention-for-salient-object-detection
37
total views0
total downloads3
views this month0
downloads this month