LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912516151443456 |
|---|---|
| author | Yan, Xinyu Sun, Meijun Ji, Ge-Peng Khan, Fahad Shahbaz Khan, Salman Fan, Deng-Ping |
| author_facet | Yan, Xinyu Sun, Meijun Ji, Ge-Peng Khan, Fahad Shahbaz Khan, Salman Fan, Deng-Ping |
| contents | We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an image-conditioned mask generation task within a latent diffusion model, enabling seamless integration of user controls. LawDIS is enhanced with macro-to-micro control modes. Specifically, in macro mode, we introduce a language-controlled segmentation strategy (LS) to generate an initial mask based on user-provided language prompts. In micro mode, a window-controlled refinement strategy (WR) allows flexible refinement of user-defined regions (i.e., size-adjustable windows) within the initial mask. Coordinated by a mode switcher, these modes can operate independently or jointly, making the framework well-suited for high-accuracy, personalised applications. Extensive experiments on the DIS5K benchmark reveal that our LawDIS significantly outperforms 11 cutting-edge methods across all metrics. Notably, compared to the second-best model MVANet, we achieve $F_β^ω$ gains of 4.6\% with both the LS and WR strategies and 3.6\% gains with only the LS strategy on DIS-TE. Codes will be made available at https://github.com/XinyuYanTJU/LawDIS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01152 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation Yan, Xinyu Sun, Meijun Ji, Ge-Peng Khan, Fahad Shahbaz Khan, Salman Fan, Deng-Ping Computer Vision and Pattern Recognition We present LawDIS, a language-window-based controllable dichotomous image segmentation (DIS) framework that produces high-quality object masks. Our framework recasts DIS as an image-conditioned mask generation task within a latent diffusion model, enabling seamless integration of user controls. LawDIS is enhanced with macro-to-micro control modes. Specifically, in macro mode, we introduce a language-controlled segmentation strategy (LS) to generate an initial mask based on user-provided language prompts. In micro mode, a window-controlled refinement strategy (WR) allows flexible refinement of user-defined regions (i.e., size-adjustable windows) within the initial mask. Coordinated by a mode switcher, these modes can operate independently or jointly, making the framework well-suited for high-accuracy, personalised applications. Extensive experiments on the DIS5K benchmark reveal that our LawDIS significantly outperforms 11 cutting-edge methods across all metrics. Notably, compared to the second-best model MVANet, we achieve $F_β^ω$ gains of 4.6\% with both the LS and WR strategies and 3.6\% gains with only the LS strategy on DIS-TE. Codes will be made available at https://github.com/XinyuYanTJU/LawDIS. |
| title | LawDIS: Language-Window-based Controllable Dichotomous Image Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.01152 |