Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well
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_ | 1866910949504450560 |
|---|---|
| author | Fang, Chengyu He, Chunming Tang, Longxiang Zhang, Yuelin Zhu, Chenyang Shen, Yuqi Chen, Chubin Xu, Guoxia Li, Xiu |
| author_facet | Fang, Chengyu He, Chunming Tang, Longxiang Zhang, Yuelin Zhu, Chenyang Shen, Yuqi Chen, Chubin Xu, Guoxia Li, Xiu |
| contents | Camouflaged Object Segmentation (COS) remains challenging because camouflaged objects exhibit only subtle visual differences from their backgrounds and single-modality RGB methods provide limited cues, leading researchers to explore multimodal data to improve segmentation accuracy. In this work, we presenet MultiCOS, a novel framework that effectively leverages diverse data modalities to improve segmentation performance. MultiCOS comprises two modules: Bi-space Fusion Segmentor (BFSer), which employs a state space and a latent space fusion mechanism to integrate cross-modal features within a shared representation and employs a fusion-feedback mechanism to refine context-specific features, and Cross-modal Knowledge Learner (CKLer), which leverages external multimodal datasets to generate pseudo-modal inputs and establish cross-modal semantic associations, transferring knowledge to COS models when real multimodal pairs are missing. When real multimodal COS data are unavailable, CKLer yields additional segmentation gains using only non-COS multimodal sources. Experiments on standard COS benchmarks show that BFSer outperforms existing multimodal baselines with both real and pseudo-modal data. Code will be released at \href{https://github.com/cnyvfang/MultiCOS}{GitHub}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14471 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well Fang, Chengyu He, Chunming Tang, Longxiang Zhang, Yuelin Zhu, Chenyang Shen, Yuqi Chen, Chubin Xu, Guoxia Li, Xiu Computer Vision and Pattern Recognition Camouflaged Object Segmentation (COS) remains challenging because camouflaged objects exhibit only subtle visual differences from their backgrounds and single-modality RGB methods provide limited cues, leading researchers to explore multimodal data to improve segmentation accuracy. In this work, we presenet MultiCOS, a novel framework that effectively leverages diverse data modalities to improve segmentation performance. MultiCOS comprises two modules: Bi-space Fusion Segmentor (BFSer), which employs a state space and a latent space fusion mechanism to integrate cross-modal features within a shared representation and employs a fusion-feedback mechanism to refine context-specific features, and Cross-modal Knowledge Learner (CKLer), which leverages external multimodal datasets to generate pseudo-modal inputs and establish cross-modal semantic associations, transferring knowledge to COS models when real multimodal pairs are missing. When real multimodal COS data are unavailable, CKLer yields additional segmentation gains using only non-COS multimodal sources. Experiments on standard COS benchmarks show that BFSer outperforms existing multimodal baselines with both real and pseudo-modal data. Code will be released at \href{https://github.com/cnyvfang/MultiCOS}{GitHub}. |
| title | Integrating Extra Modality Helps Segmentor Find Camouflaged Objects Well |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.14471 |