Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929604437999616 |
|---|---|
| author | Wu, Wangyu Dai, Tianhong Huang, Xiaowei Ma, Fei Xiao, Jimin |
| author_facet | Wu, Wangyu Dai, Tianhong Huang, Xiaowei Ma, Fei Xiao, Jimin |
| contents | Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_09760 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation Wu, Wangyu Dai, Tianhong Huang, Xiaowei Ma, Fei Xiao, Jimin Computer Vision and Pattern Recognition Weakly-supervised semantic segmentation (WSSS), which aims to train segmentation models solely using image-level labels, has achieved significant attention. Existing methods primarily focus on generating high-quality pseudo labels using available images and their image-level labels. However, the quality of pseudo labels degrades significantly when the size of available dataset is limited. Thus, in this paper, we tackle this problem from a different view by introducing a novel approach called Image Augmentation with Controlled Diffusion (IACD). This framework effectively augments existing labeled datasets by generating diverse images through controlled diffusion, where the available images and image-level labels are served as the controlling information. Moreover, we also propose a high-quality image selection strategy to mitigate the potential noise introduced by the randomness of diffusion models. In the experiments, our proposed IACD approach clearly surpasses existing state-of-the-art methods. This effect is more obvious when the amount of available data is small, demonstrating the effectiveness of our method. |
| title | Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.09760 |