arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.07246cs.CV
收藏

弱监督语义分割中的判别区域抑制

Discriminative Region Suppression for Weakly-Supervised Semantic Segmentation

Korea Advanced Institute of Science and Technology (KAIST)(韩国科学技术院)

Beomyoung Kim, Sangeun Han, Junmo Kim

摘要:

使用图像级标签的弱监督语义分割(WSSS)最近因降低标注成本而受到广泛关注。现有的WSSS方法利用来自分类网络的定位图来生成伪分割标签。然而,由于从分类器获得的定位图只集中在稀疏的判别对象区域,很难生成高质量的分割标签。为了解决这个问题,我们引入了区分区域抑制(DRS)模块,这是一种简单而有效的方法来扩展对象激活区域。DRS抑制了对区分区域的注意,并将其传播到相邻的非区分区域,生成密集的定位图。DRS只需要很少或不需要额外的参数,并且可以插入任何网络。此外,我们引入了一个额外的学习策略,以提供一个自我增强的本地化地图,命名为本地化地图细化学习。受益于这种细化学习,定位地图通过恢复一些丢失的部分或去除噪声本身来细化和增强。由于其简单性和有效性,我们的方法仅使用图像级标签在PASCAL VOC 2012分割基准上实现了mIoU 71.4%。大量的实验证明了我们方法的有效性。该代码可在https://github.com/qjadud1994/DRS上获得。

英文摘要:

Weakly-supervised semantic segmentation (WSSS) using image-level labels has recently attracted much attention for reducing annotation costs. Existing WSSS methods utilize localization maps from the classification network to generate pseudo segmentation labels. However, since localization maps obtained from the classifier focus only on sparse discriminative object regions, it is difficult to generate high-quality segmentation labels. To address this issue, we introduce discriminative region suppression (DRS) module that is a simple yet effective method to expand object activation regions. DRS suppresses the attention on discriminative regions and spreads it to adjacent non-discriminative regions, generating dense localization maps. DRS requires few or no additional parameters and can be plugged into any network. Furthermore, we introduce an additional learning strategy to give a self-enhancement of localization maps, named localization map refinement learning. Benefiting from this refinement learning, localization maps are refined and enhanced by recovering some missing parts or removing noise itself. Due to its simplicity and effectiveness, our approach achieves mIoU 71.4% on the PASCAL VOC 2012 segmentation benchmark using only image-level labels. Extensive experiments demonstrate the effectiveness of our approach. The code is available at https://github.com/qjadud1994/DRS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑