Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911900293398528 |
|---|---|
| author | Wu, Biao Zhang, Diankai Gao, Si Zheng, Chengjian Liu, Shaoli Wang, Ning |
| author_facet | Wu, Biao Zhang, Diankai Gao, Si Zheng, Chengjian Liu, Shaoli Wang, Ning |
| contents | Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_00587 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024 Wu, Biao Zhang, Diankai Gao, Si Zheng, Chengjian Liu, Shaoli Wang, Ning Computer Vision and Pattern Recognition Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image. Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction,because the real-world is actually video-based rather than a static state. In this paper, we adopt semi-supervised video semantic segmentation method based on unreliable pseudo labels. Then, We ensemble the teacher network model with the student network model to generate pseudo labels and retrain the student network. Our method achieves the mIoU scores of 63.71% and 67.83% on development test and final test respectively. Finally, we obtain the 1st place in the Video Scene Parsing in the Wild Challenge at CVPR 2024. |
| title | Semi-supervised Video Semantic Segmentation Using Unreliable Pseudo Labels for PVUW2024 |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2406.00587 |