Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation | |
Changwei Wang1,3; Rongtao Xu1,3; Shibiao Xu2; Weiliang Meng1,3; Xiaopeng Zhang1,3 | |
2023 | |
会议日期 | 2023 |
会议地点 | 法国巴黎 |
英文摘要 | Generating accurate pseudo-labels under the supervision of image categories is a crucial step in Weakly Supervised Semantic Segmentation (WSSS). In this work, we propose a Mat-Label pipeline that provides a fresh way to treat WSSS pseudo-labels generation as an image matting task. By taking a trimap as input which specifies the foreground, background and unknown regions, the image matting task outputs an object mask with fine edges. The intuition behind our Mat-Label is that generating trimap is much easier than generating pseudo-labels directly under weakly supervised setting. Although current CAM-based methods are off-the-shelf solutions for generating a trimap, they suffer from cross-category and foreground-background pixel prediction confusion. To solve this problem, we develop a Double Decoupled Class Activation Map (D2CAM) for Mat-Label to generate a high-quality trimap. By drawing on the idea of metric learning, we explicitly model class activation map with category decoupling and foregroundbackground decoupling. We also design two simple yet effective refinement constraints for D2CAM to stabilize optimization and eliminate non-exclusive activation. Extensive experiments validate that our Mat-Label achieves substantial and consistent performance gains compared to current state-of-the-art WSSS approaches. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/56664] |
专题 | 模式识别国家重点实验室_三维可视计算 |
通讯作者 | Shibiao Xu; Weiliang Meng |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, China 2.School of Artificial Intelligence, Beijing University of Posts and Telecommunications, China 3.The State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, China |
推荐引用方式 GB/T 7714 | Changwei Wang,Rongtao Xu,Shibiao Xu,et al. Treating Pseudo-labels Generation as Image Matting for Weakly Supervised Semantic Segmentation[C]. 见:. 法国巴黎. 2023. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论