Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915622606077952 |
|---|---|
| author | Wen, Yu Gao, Shuyong Zhang, Shuping Huang, Miao Tao, Lili Yang, Han Xing, Haozhe Zhang, Lihe Hou, Boxue |
| author_facet | Wen, Yu Gao, Shuyong Zhang, Shuping Huang, Miao Tao, Lili Yang, Han Xing, Haozhe Zhang, Lihe Hou, Boxue |
| contents | Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into one-dimensional prompts, yielding significant results. We explore ways to enhance performance through multi-context fusion of rich salient image features and camouflaged object features. Therefore, we propose RFMNet, which utilizes features from multiple encoding stages of the reference salient images and performs interactive fusion with the camouflage features at the corresponding encoding stages. Given that the features in salient object images contain abundant object-related detail information, performing feature fusion within local areas is more beneficial for detecting camouflaged objects. Therefore, we propose an Overlapped Windows Cross-attention mechanism to enable the model to focus more attention on the local information matching based on reference features. Besides, we propose the Referring Feature Aggregation (RFA) module to decode and segment the camouflaged objects progressively. Extensive experiments on the Ref-COD benchmark demonstrate that our method achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13249 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention Wen, Yu Gao, Shuyong Zhang, Shuping Huang, Miao Tao, Lili Yang, Han Xing, Haozhe Zhang, Lihe Hou, Boxue Computer Vision and Pattern Recognition Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into one-dimensional prompts, yielding significant results. We explore ways to enhance performance through multi-context fusion of rich salient image features and camouflaged object features. Therefore, we propose RFMNet, which utilizes features from multiple encoding stages of the reference salient images and performs interactive fusion with the camouflage features at the corresponding encoding stages. Given that the features in salient object images contain abundant object-related detail information, performing feature fusion within local areas is more beneficial for detecting camouflaged objects. Therefore, we propose an Overlapped Windows Cross-attention mechanism to enable the model to focus more attention on the local information matching based on reference features. Besides, we propose the Referring Feature Aggregation (RFA) module to decode and segment the camouflaged objects progressively. Extensive experiments on the Ref-COD benchmark demonstrate that our method achieves state-of-the-art performance. |
| title | Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.13249 |