S 2 AM: Dynamic Center–Surround Mechanism for Remote Sensing Salient Object Detection.
Saved in:
| Title: | S 2 AM: Dynamic Center–Surround Mechanism for Remote Sensing Salient Object Detection. |
|---|---|
| Authors: | Sha, Yuzhe1 (AUTHOR), Tan, Zhenshan1 (AUTHOR) zstan@nuist.edu.cn, Huo, Xuejin1 (AUTHOR), Liu, Rui1 (AUTHOR), Luo, Zhanxin1 (AUTHOR), Chen, Xianyi1 (AUTHOR) |
| Source: | Remote Sensing. May2026, Vol. 18 Issue 10, p1490. 27p. |
| Subjects: | Remote sensing, Optical remote sensing, Visual perception, Deep learning |
| Abstract: | Highlights: What are the main findings? A dynamic center–surround mechanism is proposed to explicitly model spatial contrast for remote sensing salient object detection. The proposed S2AM framework effectively captures semantic centroids and adaptive surround contrast, achieving robust saliency localization in complex remote sensing scenes. What are the implications of the main findings? This work provides a new perspective for remote sensing saliency detection by integrating center–surround modeling into deep learning frameworks. The proposed framework improves saliency detection by explicitly modeling center–surround relationships, enabling more stable localization under complex scene conditions. Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) aims to localize visually dominant regions in large-scale remote sensing scenes for applications such as disaster monitoring and urban analysis. Visual saliency fundamentally arises from contrast between a local region and its surrounding context, i.e., the center–surround mechanism. While ORSI-SOD further extends this principle, existing methods still rely on implicit or weak center bias and lack explicit modeling of center–surround spatial contrast, resulting in unstable saliency localization in complex remote sensing scenes. To address this issue, inspired by the human visual system, we propose a saliency detection framework based on SAM2 that explicitly embodies a dynamic center–surround mechanism, termed S2AM. S2AM explicitly reconstructs the saliency localization process by jointly modeling heterogeneous saliency cues, including semantic centers, surround contrast, and boundary constraints in a prompt-free manner. Specifically, we introduce a Saliency-Aware Domain Adapter (SADA) to inject saliency-sensitive activations into generic foundation features, alleviating the weak and implicit center bias inherited from SAM2. Building upon this, a Centroid-Guided Coarse Localization (CGCL) module explicitly predicts semantic centroids and constructs adaptive center–surround contrast structures, enabling robust localization under highly variable object distributions. Finally, a Structure-Constrained Saliency Location Decoder (SCLD) leverages structural cues as spatial constraints to enhance center saliency and suppress surrounding interference. Extensive experiments on the EORSSD, ORSSD, and ORSI-4199 benchmarks demonstrate that S2AM consistently outperforms state-of-the-art methods across multiple evaluation metrics, validating the effectiveness of dynamic center–surround-driven saliency modeling for challenging remote sensing scenarios. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? A dynamic center–surround mechanism is proposed to explicitly model spatial contrast for remote sensing salient object detection. The proposed S2AM framework effectively captures semantic centroids and adaptive surround contrast, achieving robust saliency localization in complex remote sensing scenes. What are the implications of the main findings? This work provides a new perspective for remote sensing saliency detection by integrating center–surround modeling into deep learning frameworks. The proposed framework improves saliency detection by explicitly modeling center–surround relationships, enabling more stable localization under complex scene conditions. Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) aims to localize visually dominant regions in large-scale remote sensing scenes for applications such as disaster monitoring and urban analysis. Visual saliency fundamentally arises from contrast between a local region and its surrounding context, i.e., the center–surround mechanism. While ORSI-SOD further extends this principle, existing methods still rely on implicit or weak center bias and lack explicit modeling of center–surround spatial contrast, resulting in unstable saliency localization in complex remote sensing scenes. To address this issue, inspired by the human visual system, we propose a saliency detection framework based on SAM2 that explicitly embodies a dynamic center–surround mechanism, termed S2AM. S2AM explicitly reconstructs the saliency localization process by jointly modeling heterogeneous saliency cues, including semantic centers, surround contrast, and boundary constraints in a prompt-free manner. Specifically, we introduce a Saliency-Aware Domain Adapter (SADA) to inject saliency-sensitive activations into generic foundation features, alleviating the weak and implicit center bias inherited from SAM2. Building upon this, a Centroid-Guided Coarse Localization (CGCL) module explicitly predicts semantic centroids and constructs adaptive center–surround contrast structures, enabling robust localization under highly variable object distributions. Finally, a Structure-Constrained Saliency Location Decoder (SCLD) leverages structural cues as spatial constraints to enhance center saliency and suppress surrounding interference. Extensive experiments on the EORSSD, ORSSD, and ORSI-4199 benchmarks demonstrate that S2AM consistently outperforms state-of-the-art methods across multiple evaluation metrics, validating the effectiveness of dynamic center–surround-driven saliency modeling for challenging remote sensing scenarios. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18101490 |
