Employing multi-estimations for weakly-supervised semantic segmentation | |
Fan, Junsong1,2; Zhang, Zhaoxiang1,2,3; Tan, Tieniu1,2,3 | |
2020 | |
会议名称 | European Conference on Computer Vision (ECCV) |
会议日期 | 2020 |
会议地点 | Online |
摘要 | Image-level label based weakly-supervised semantic segmentation (WSSS) aims to adopt image-level labels to train semantic segmentation models, saving vast human labors for costly pixel-level annotations. A typical pipeline for this problem is first to adopt class activation maps (CAM) with image-level labels to generate pseudo-masks (a.k.a. seeds) and then use them for training segmentation models. The main difficulty is that seeds are usually sparse and incomplete. Related works typically try to alleviate this problem by adopting many bells and whistles to enhance the seeds. Instead of struggling to refine a single seed, we propose a novel approach to alleviate the inaccurate seed problem by leveraging the segmentation model’s robustness to learn from multiple seeds. We managed to generate many different seeds for each image, which are different estimates of the underlying ground truth. The segmentation model simultaneously exploits these seeds to learn and automatically decides the confidence of each seed. Extensive experiments on Pascal VOC 2012 demonstrate the advantage of this multi-seeds strategy over previous state-of-the-art. |
关键词 | weakly supervised learning semantic segmentation |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48760 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Zhang, Zhaoxiang |
作者单位 | 1.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) 2.School of Artificial Intelligence, University of Chinese Academy of Sciences (UCAS) 3.Center for Excellence in Brain Science and Intelligence Technology, CAS |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Fan, Junsong,Zhang, Zhaoxiang,Tan, Tieniu. Employing multi-estimations for weakly-supervised semantic segmentation[C],2020. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
123620324.pdf(2884KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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