papers AI Learner
The Github is limit! Click to go to the new site.

Closed-Loop Adaptation for Weakly-Supervised Semantic Segmentation

2019-05-29
Zhengqiang Zhang, Shujian Yu, Shi Yin, Qinmu Peng, Xinge You

Abstract

Weakly-supervised semantic segmentation aims to assign each pixel a semantic category under weak supervisions, such as image-level tags. Most of existing weakly-supervised semantic segmentation methods do not use any feedback from segmentation output and can be considered as open-loop systems. They are prone to accumulated errors because of the static seeds and the sensitive structure information. In this paper, we propose a generic self-adaptation mechanism for existing weakly-supervised semantic segmentation methods by introducing two feedback chains, thus constituting a closed-loop system. Specifically, the first chain iteratively produces dynamic seeds by incorporating cross-image structure information, whereas the second chain further expands seed regions by a customized random walk process to reconcile inner-image structure information characterized by superpixels. Experiments on PASCAL VOC 2012 suggest that our network outperforms state-of-the-art methods with significantly less computational and memory burden.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.12190

PDF

http://arxiv.org/pdf/1905.12190


Similar Posts

Comments