Scene context-aware salient object detection
Salient object detection identifies objects in an image that grab visual attention. Although contextual features are considered in recent literature, they often fail in real-world complex scenarios. We observe that this is mainly due to two issues: First, most existing datasets consist of simple for...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
IEEE
2022
|
| _version_ | 1797061313635024896 |
|---|---|
| author | Siris, A Jiao, J Tam, GKL Xie, X Lau, RWH |
| author_facet | Siris, A Jiao, J Tam, GKL Xie, X Lau, RWH |
| author_sort | Siris, A |
| collection | OXFORD |
| description | Salient object detection identifies objects in an image that grab visual attention. Although contextual features are considered in recent literature, they often fail in real-world complex scenarios. We observe that this is mainly due to two issues: First, most existing datasets consist of simple foregrounds and backgrounds that hardly represent real-life scenarios. Second, current methods only learn contextual features of salient objects, which are insufficient to model high-level semantics for saliency reasoning in complex scenes. To address these problems, we first construct a new large-scale dataset with complex scenes in this paper. We then propose a context-aware learning approach to explicitly exploit the semantic scene contexts. Specifically, two modules are proposed to achieve the goal: 1) a Semantic Scene Context Refinement module to enhance contextual features learned from salient objects with scene context, and 2) a Contextual Instance Transformer to learn contextual relations between objects and scene context. To our knowledge, such high-level semantic contextual information of image scenes is under-explored for saliency detection in the literature. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art techniques in complex scenarios for saliency detection, and transfers well to other existing datasets. The code and dataset are available at https://github.com/SirisAvishek/Scene_Context_Aware_Saliency.
|
| first_indexed | 2024-03-06T20:29:19Z |
| format | Conference item |
| id | oxford-uuid:3084e3a0-fb7e-4e01-a168-b2e9f46e1e07 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T20:29:19Z |
| publishDate | 2022 |
| publisher | IEEE |
| record_format | dspace |
| spelling | oxford-uuid:3084e3a0-fb7e-4e01-a168-b2e9f46e1e072022-03-26T13:01:55ZScene context-aware salient object detectionConference itemhttp://purl.org/coar/resource_type/c_5794uuid:3084e3a0-fb7e-4e01-a168-b2e9f46e1e07EnglishSymplectic ElementsIEEE2022Siris, AJiao, JTam, GKLXie, XLau, RWHSalient object detection identifies objects in an image that grab visual attention. Although contextual features are considered in recent literature, they often fail in real-world complex scenarios. We observe that this is mainly due to two issues: First, most existing datasets consist of simple foregrounds and backgrounds that hardly represent real-life scenarios. Second, current methods only learn contextual features of salient objects, which are insufficient to model high-level semantics for saliency reasoning in complex scenes. To address these problems, we first construct a new large-scale dataset with complex scenes in this paper. We then propose a context-aware learning approach to explicitly exploit the semantic scene contexts. Specifically, two modules are proposed to achieve the goal: 1) a Semantic Scene Context Refinement module to enhance contextual features learned from salient objects with scene context, and 2) a Contextual Instance Transformer to learn contextual relations between objects and scene context. To our knowledge, such high-level semantic contextual information of image scenes is under-explored for saliency detection in the literature. Extensive experiments demonstrate that the proposed approach outperforms state-of-the-art techniques in complex scenarios for saliency detection, and transfers well to other existing datasets. The code and dataset are available at https://github.com/SirisAvishek/Scene_Context_Aware_Saliency. |
| spellingShingle | Siris, A Jiao, J Tam, GKL Xie, X Lau, RWH Scene context-aware salient object detection |
| title | Scene context-aware salient object detection |
| title_full | Scene context-aware salient object detection |
| title_fullStr | Scene context-aware salient object detection |
| title_full_unstemmed | Scene context-aware salient object detection |
| title_short | Scene context-aware salient object detection |
| title_sort | scene context aware salient object detection |
| work_keys_str_mv | AT sirisa scenecontextawaresalientobjectdetection AT jiaoj scenecontextawaresalientobjectdetection AT tamgkl scenecontextawaresalientobjectdetection AT xiex scenecontextawaresalientobjectdetection AT laurwh scenecontextawaresalientobjectdetection |