Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2409.07238 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909311693750272 |
|---|---|
| author | Lu, Yingling Yang, Yijun Xing, Zhaohu Wang, Qiong Zhu, Lei |
| author_facet | Lu, Yingling Yang, Yijun Xing, Zhaohu Wang, Qiong Zhu, Lei |
| contents | Diffusion Probabilistic Models have recently attracted significant attention in the community of computer vision due to their outstanding performance. However, while a substantial amount of diffusion-based research has focused on generative tasks, no work introduces diffusion models to advance the results of polyp segmentation in videos, which is frequently challenged by polyps' high camouflage and redundant temporal cues.In this paper, we present a novel diffusion-based network for video polyp segmentation task, dubbed as Diff-VPS. We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation. This integrates the contextual high-level information achieved by the joint classification and detection tasks. To explore the temporal dependency, Temporal Reasoning Module (TRM) is devised via reasoning and reconstructing the target frame from the previous frames. We further equip TRM with a generative adversarial self-supervised strategy to produce more realistic frames and thus capture better dynamic cues. Extensive experiments are conducted on SUN-SEG, and the results indicate that our proposed Diff-VPS significantly achieves state-of-the-art performance. Code is available at https://github.com/lydia-yllu/Diff-VPS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07238 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal Reasoning Lu, Yingling Yang, Yijun Xing, Zhaohu Wang, Qiong Zhu, Lei Computer Vision and Pattern Recognition Information Retrieval Diffusion Probabilistic Models have recently attracted significant attention in the community of computer vision due to their outstanding performance. However, while a substantial amount of diffusion-based research has focused on generative tasks, no work introduces diffusion models to advance the results of polyp segmentation in videos, which is frequently challenged by polyps' high camouflage and redundant temporal cues.In this paper, we present a novel diffusion-based network for video polyp segmentation task, dubbed as Diff-VPS. We incorporate multi-task supervision into diffusion models to promote the discrimination of diffusion models on pixel-by-pixel segmentation. This integrates the contextual high-level information achieved by the joint classification and detection tasks. To explore the temporal dependency, Temporal Reasoning Module (TRM) is devised via reasoning and reconstructing the target frame from the previous frames. We further equip TRM with a generative adversarial self-supervised strategy to produce more realistic frames and thus capture better dynamic cues. Extensive experiments are conducted on SUN-SEG, and the results indicate that our proposed Diff-VPS significantly achieves state-of-the-art performance. Code is available at https://github.com/lydia-yllu/Diff-VPS. |
| title | Diff-VPS: Video Polyp Segmentation via a Multi-task Diffusion Network with Adversarial Temporal Reasoning |
| topic | Computer Vision and Pattern Recognition Information Retrieval |
| url | https://arxiv.org/abs/2409.07238 |