Please use this identifier to cite or link to this item:
Title: Multi-level adversarial network for domain adaptive semantic segmentation
Authors: Huang, Jiaxing
Guan, Dayan
Xiao, Aoran
Lu, Shijian
Keywords: Engineering::Computer science and engineering
Issue Date: 2022
Source: Huang, J., Guan, D., Xiao, A. & Lu, S. (2022). Multi-level adversarial network for domain adaptive semantic segmentation. Pattern Recognition, 123, 108384-.
Journal: Pattern Recognition
Abstract: Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space (i.e., image-to-image translation) and output space (i.e., self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets.
ISSN: 0031-3203
DOI: 10.1016/j.patcog.2021.108384
Rights: © 2021 Elsevier Ltd. All rights reserved. This paper was published in Pattern Recognition and is made available with permission of Elsevier Ltd.
Fulltext Permission: embargo_20240407
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
Multi-level adversarial network for domain adaptive semantic segmentation.pdf
  Until 2024-04-07
3.52 MBAdobe PDFUnder embargo until Apr 07, 2024

Page view(s)

Updated on Jul 5, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.