Can I read Multi-level Adversarial Network for Domain Adaptive Semantic Segmentation on EtoBox?

Multi-level Adversarial Network for Domain Adaptive Semantic Segmentation by Jiaxing Huang; Dayan Guan; Aoran Xiao; Shijian Lu is a Computer Science article available to read on EtoBox.

What is Multi-level Adversarial Network for Domain Adaptive Semantic Segmentation about?

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 consi

Who reads Multi-level Adversarial Network for Domain Adaptive Semantic Segmentation?

Author

Jiaxing Huang; Dayan Guan; Aoran Xiao; Shijian Lu

Publisher

Elsevier BV

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)