Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation | |
Song, Chunfeng1,2; Huang, Yang1,2; Ouyang, Wanli3; Wang, Liang1,2,4,5 | |
2019-06 | |
会议名称 | IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 2019-6 |
会议地点 | Long Beach, USA |
摘要 | Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN based models severely rely on the amounts of pixel-level annotations which are expensive and time-consuming. To address this problem, it is a good choice to learn to segment with weak supervision from bounding boxes. How to make full use of the class-level and region-level supervisions from bounding boxes is the critical challenge for the weakly supervised learning task. In this paper, we first introduce a box-driven class-wise masking model (BCM) to remove irrelevant regions of each class. Moreover, based on the pixel-level segment proposal generated from the bounding box supervision, we could calculate the mean filling rates of each class to serve as an important prior cue, then we propose a filling rate guided adaptive loss (FR-Loss) to help the model ignore the wrongly labeled pixels in proposals. Unlike previous methods directly training models with the fixed individual segment proposals, our method can adjust the model learning with global statistical information. Thus it can help reduce the negative impacts from wrongly labeled proposals. We evaluate the proposed method on the challenging PASCAL VOC 2012 benchmark and compare with other methods. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results. |
关键词 | 弱监督分割 |
学科门类 | 工学::控制科学与工程 |
七大方向——子方向分类 | 知识表示与推理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28370 |
专题 | 智能感知与计算 |
通讯作者 | Song, Chunfeng |
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.The University of Sydney, SenseTime Computer Vision Research Group, Australia 3.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) 4.Chinese Academy of Sciences - Artificial Intelligence Research (CAS-AIR) 5.University of Chinese Academy of Sciences (UCAS) |
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 | Song, Chunfeng,Huang, Yang,Ouyang, Wanli,et al. Box-driven Class-wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation[C],2019. |
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 | ||
Song_Box-Driven_WSSS(1395KB) | 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