Revisiting Salient Object Detection from an Observer-Centric Perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912884000292864 |
|---|---|
| author | Zhang, Fuxi Wang, Yifan Zhao, Hengrun Sun, Zhuohan Xia, Changxing Wang, Lijun Lu, Huchuan Shao, Yangrui Yang, Chen Teng, Long |
| author_facet | Zhang, Fuxi Wang, Yifan Zhao, Hengrun Sun, Zhuohan Xia, Changxing Wang, Lijun Lu, Huchuan Shao, Yangrui Yang, Chen Teng, Long |
| contents | Salient object detection is inherently a subjective problem, as observers with different priors may perceive different objects as salient. However, existing methods predominantly formulate it as an objective prediction task with a single groundtruth segmentation map for each image, which renders the problem under-determined and fundamentally ill-posed. To address this issue, we propose Observer-Centric Salient Object Detection (OC-SOD), where salient regions are predicted by considering not only the visual cues but also the observer-specific factors such as their preferences or intents. As a result, this formulation captures the intrinsic ambiguity and diversity of human perception, enabling personalized and context-aware saliency prediction. By leveraging multi-modal large language models, we develop an efficient data annotation pipeline and construct the first OC-SOD dataset named OC-SODBench, comprising 33k training, validation and test images with 152k textual prompts and object pairs. Built upon this new dataset, we further design OC-SODAgent, an agentic baseline which performs OC-SOD via a human-like "Perceive-Reflect-Adjust" process. Extensive experiments on our proposed OC-SODBench have justified the effectiveness of our contribution. Through this observer-centric perspective, we aim to bridge the gap between human perception and computational modeling, offering a more realistic and flexible understanding of what makes an object truly "salient." Code and dataset are publicly available at: https://github.com/Dustzx/OC_SOD |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06369 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Revisiting Salient Object Detection from an Observer-Centric Perspective Zhang, Fuxi Wang, Yifan Zhao, Hengrun Sun, Zhuohan Xia, Changxing Wang, Lijun Lu, Huchuan Shao, Yangrui Yang, Chen Teng, Long Computer Vision and Pattern Recognition Artificial Intelligence Salient object detection is inherently a subjective problem, as observers with different priors may perceive different objects as salient. However, existing methods predominantly formulate it as an objective prediction task with a single groundtruth segmentation map for each image, which renders the problem under-determined and fundamentally ill-posed. To address this issue, we propose Observer-Centric Salient Object Detection (OC-SOD), where salient regions are predicted by considering not only the visual cues but also the observer-specific factors such as their preferences or intents. As a result, this formulation captures the intrinsic ambiguity and diversity of human perception, enabling personalized and context-aware saliency prediction. By leveraging multi-modal large language models, we develop an efficient data annotation pipeline and construct the first OC-SOD dataset named OC-SODBench, comprising 33k training, validation and test images with 152k textual prompts and object pairs. Built upon this new dataset, we further design OC-SODAgent, an agentic baseline which performs OC-SOD via a human-like "Perceive-Reflect-Adjust" process. Extensive experiments on our proposed OC-SODBench have justified the effectiveness of our contribution. Through this observer-centric perspective, we aim to bridge the gap between human perception and computational modeling, offering a more realistic and flexible understanding of what makes an object truly "salient." Code and dataset are publicly available at: https://github.com/Dustzx/OC_SOD |
| title | Revisiting Salient Object Detection from an Observer-Centric Perspective |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.06369 |