A Componentwise Approach to Weakly Supervised Semantic Segmentation Using Dual-Feedback Network

Zhengqiang Zhang, Qinmu Peng*, Sichao Fu, Wenjie Wang, Yiu-Ming Cheung, Yue Zhao, Shujian Yu, Xinge You

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

7 Citations (Scopus)

Abstract

Recent weakly supervised semantic segmentation methods generate pseudolabels to recover the lost position information in weak labels for training the segmentation network. Unfortunately, those pseudolabels often contain mislabeled regions and inaccurate boundaries due to the incomplete recovery of position information. It turns out that the result of semantic segmentation becomes determinate to a certain degree. In this article, we decompose the position information into two components: high-level semantic information and low-level physical information, and develop a componentwise approach to recover each component independently. Specifically, we propose a simple yet effective pseudolabels updating mechanism to iteratively correct mislabeled regions inside objects to precisely refine high-level semantic information. To reconstruct low-level physical information, we utilize a customized superpixel-based random walk mechanism to trim the boundaries. Finally, we design a novel network architecture, namely, a dual-feedback network (DFN), to integrate the two mechanisms into a unified model. Experiments on benchmark datasets show that DFN outperforms the existing state-of-the-art methods in terms of intersection-over-union (mIoU).

Original languageEnglish
Pages (from-to)7541-7554
Number of pages14
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume34
Issue number10
Early online date4 Feb 2022
DOIs
Publication statusPublished - Oct 2023

User-Defined Keywords

  • Componentwise approach
  • dual-feedback network (DFN)
  • weakly supervised semantic segmentation
  • deep learning

Fingerprint

Dive into the research topics of 'A Componentwise Approach to Weakly Supervised Semantic Segmentation Using Dual-Feedback Network'. Together they form a unique fingerprint.

Cite this