Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation
The existence of camouflage targets is widespread in the natural world, as they blend seamlessly or closely resemble their surrounding environment, making it difficult for the human eye to identify them accurately. In camouflage target segmentation, challenges often arise from the high similarity be...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/5/821 |
| _version_ | 1797264620951437312 |
|---|---|
| author | Chuanjiang Wang Yuepeng Li Guohui Wei Xiankai Hou Xiujuan Sun |
| author_facet | Chuanjiang Wang Yuepeng Li Guohui Wei Xiankai Hou Xiujuan Sun |
| author_sort | Chuanjiang Wang |
| collection | DOAJ |
| description | The existence of camouflage targets is widespread in the natural world, as they blend seamlessly or closely resemble their surrounding environment, making it difficult for the human eye to identify them accurately. In camouflage target segmentation, challenges often arise from the high similarity between the foreground and background, resulting in segmentation errors, imprecise edge detection, and overlooking of small targets. To address these issues, this paper presents a robust localization-guided dual-branch network for the recognition of camouflaged targets. Two crucial branches, i.e., a localization branch and an overall refinement branch are designed and incorporated. The localization branch achieves accurate preliminary localization of camouflaged targets by incorporating the robust localization module, which integrates different high-level feature maps in a partially decoded manner. The overall refinement branch optimizes segmentation accuracy based on the output predictions of the localization branch. Within this branch, the edge refinement module is devised to effectively reduce false negative and false positive interference. By conducting context exploration on each feature layer from top to bottom, this module further enhances the precision of target edge segmentation. Additionally, our network employs five jointly trained output prediction maps and introduces attention-guided heads for diverse prediction maps in the overall refinement branch. This design adjusts the spatial positions and channel weights of different prediction maps, generating output prediction maps based on the emphasis of each output, thereby further strengthening the perception and feature representation capabilities of the model. To improve its ability to generate highly confident and accurate prediction candidate regions, tailored loss functions are designed to cater to the objectives of different prediction maps. We conducted experiments on three publicly available datasets for camouflaged object detection to assess our methodology and compared it with state-of-the-art network models. On the largest dataset COD10K, our method achieved a Structure-measure of 0.827 and demonstrated superior performance in other evaluation metrics, outperforming recent network models. |
| first_indexed | 2024-04-25T00:31:48Z |
| format | Article |
| id | doaj.art-039379d75819433ba306a893ed30c89c |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-25T00:31:48Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-039379d75819433ba306a893ed30c89c2024-03-12T16:42:16ZengMDPI AGElectronics2079-92922024-02-0113582110.3390/electronics13050821Robust Localization-Guided Dual-Branch Network for Camouflaged Object SegmentationChuanjiang Wang0Yuepeng Li1Guohui Wei2Xiankai Hou3Xiujuan Sun4College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, ChinaCollege of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, ChinaThe existence of camouflage targets is widespread in the natural world, as they blend seamlessly or closely resemble their surrounding environment, making it difficult for the human eye to identify them accurately. In camouflage target segmentation, challenges often arise from the high similarity between the foreground and background, resulting in segmentation errors, imprecise edge detection, and overlooking of small targets. To address these issues, this paper presents a robust localization-guided dual-branch network for the recognition of camouflaged targets. Two crucial branches, i.e., a localization branch and an overall refinement branch are designed and incorporated. The localization branch achieves accurate preliminary localization of camouflaged targets by incorporating the robust localization module, which integrates different high-level feature maps in a partially decoded manner. The overall refinement branch optimizes segmentation accuracy based on the output predictions of the localization branch. Within this branch, the edge refinement module is devised to effectively reduce false negative and false positive interference. By conducting context exploration on each feature layer from top to bottom, this module further enhances the precision of target edge segmentation. Additionally, our network employs five jointly trained output prediction maps and introduces attention-guided heads for diverse prediction maps in the overall refinement branch. This design adjusts the spatial positions and channel weights of different prediction maps, generating output prediction maps based on the emphasis of each output, thereby further strengthening the perception and feature representation capabilities of the model. To improve its ability to generate highly confident and accurate prediction candidate regions, tailored loss functions are designed to cater to the objectives of different prediction maps. We conducted experiments on three publicly available datasets for camouflaged object detection to assess our methodology and compared it with state-of-the-art network models. On the largest dataset COD10K, our method achieved a Structure-measure of 0.827 and demonstrated superior performance in other evaluation metrics, outperforming recent network models.https://www.mdpi.com/2079-9292/13/5/821camouflaged objects segmentationmulti-scale featureattention mechanismFPN |
| spellingShingle | Chuanjiang Wang Yuepeng Li Guohui Wei Xiankai Hou Xiujuan Sun Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation Electronics camouflaged objects segmentation multi-scale feature attention mechanism FPN |
| title | Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation |
| title_full | Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation |
| title_fullStr | Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation |
| title_full_unstemmed | Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation |
| title_short | Robust Localization-Guided Dual-Branch Network for Camouflaged Object Segmentation |
| title_sort | robust localization guided dual branch network for camouflaged object segmentation |
| topic | camouflaged objects segmentation multi-scale feature attention mechanism FPN |
| url | https://www.mdpi.com/2079-9292/13/5/821 |
| work_keys_str_mv | AT chuanjiangwang robustlocalizationguideddualbranchnetworkforcamouflagedobjectsegmentation AT yuepengli robustlocalizationguideddualbranchnetworkforcamouflagedobjectsegmentation AT guohuiwei robustlocalizationguideddualbranchnetworkforcamouflagedobjectsegmentation AT xiankaihou robustlocalizationguideddualbranchnetworkforcamouflagedobjectsegmentation AT xiujuansun robustlocalizationguideddualbranchnetworkforcamouflagedobjectsegmentation |