.png){kind=icon}
返回
Multi-level adversarial network for domain adaptive semantic segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2021.108384.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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. (c) 2021 Elsevier Ltd. All rights reserved.
Keyword:
Unsupervised domain adaptation
Semantic segmentation
Adversarial learning
Self training
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Scale variance minimization for unsupervised domain adaptation in image segmentation.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Active multi-kernel domain adaptation for hyperspectral image classificationPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Correlation-aware adversarial domain adaptation and generalization相关感知的对抗域适应和泛化PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Exploring uncertainty in pseudo-label guided unsupervised domain adaptation探索伪标签引导的无监督域自适应中的不确定性PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏More time for judo matches? Analysis of type of techniques, time, scores, and penalties in the Tokyo 2020 Olympic Games更多时间进行柔道比赛？东京2020奥运会技术类型、时间、得分和处罚分析OAAI
OAAI分享收藏
没有更多内容
没有更多内容