arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.07021cs.CV
收藏

MuSCLe:一个弱监督语义分割的多策略对比学习框架

MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation

Loughborough University(拉夫堡大学);Cardiff University(卡迪夫大学);Central South University(中南大学)

Kunhao Yuan, Gerald Schaefer, Yu-Kun Lai, Yifan Wang, Xiyao Liu, Lin Guan, Hui Fang

摘要:

弱监督语义分割(WSSS)已经获得了显着的普及,因为它只依赖于弱标签,如图像级注释,而不是像素级注释所需的监督语义分割(SSS)方法。尽管注释成本大大降低,但从WSSS学习的典型特征表示仅代表对象的一些突出部分,并且由于训练期间的弱指导,与SSS相比不太可靠。在本文中,我们提出了一种新的多策略对比学习(MuSCLe)框架,以获得增强的特征表示,并通过利用图像,区域,像素和对象边界级别的对比样本对的相似性和不相似性,提高WSSS性能。大量的实验证明了我们的方法的有效性,并表明MuSCLe在广泛使用的PASCAL VOC 2012数据集上的性能优于当前最先进的技术。

英文摘要:

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods. Despite drastically reduced annotation costs, typical feature representations learned from WSSS are only representative of some salient parts of objects and less reliable compared to SSS due to the weak guidance during training. In this paper, we propose a novel Multi-Strategy Contrastive Learning (MuSCLe) framework to obtain enhanced feature representations and improve WSSS performance by exploiting similarity and dissimilarity of contrastive sample pairs at image, region, pixel and object boundary levels. Extensive experiments demonstrate the effectiveness of our method and show that MuSCLe outperforms the current state-of-the-art on the widely used PASCAL VOC 2012 dataset.

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。

↑