Multi-source Domain Adaptation for Semantic Segmentation

2019-10-27 · NeurIPS 2019 12 · Sicheng Zhao, Bo Li, Xiangyu Yue, Yang Gu, Pengfei Xu, Runbo Hu, Hua Chai, Kurt Keutzer

Simulation-to-real domain adaptation for semantic segmentation has been actively studied for various applications such as autonomous driving. Existing methods mainly focus on a single-source setting, which cannot easily handle a more practical scenario of multiple sources with different distributions. In this paper, we propose to investigate multi-source domain adaptation for semantic segmentation. Specifically, we design a novel framework, termed Multi-source Adversarial Domain Aggregation Network (MADAN), which can be trained in an end-to-end manner. First, we generate an adapted domain for each source with dynamic semantic consistency while aligning at the pixel-level cycle-consistently towards the target. Second, we propose sub-domain aggregation discriminator and cross-domain cycle discriminator to make different adapted domains more closely aggregated. Finally, feature-level alignment is performed between the aggregated domain and target domain while training the segmentation network. Extensive experiments from synthetic GTA and SYNTHIA to real Cityscapes and BDDS datasets demonstrate that the proposed MADAN model outperforms state-of-the-art approaches. Our source code is released at: https://github.com/Luodian/MADAN.

📄 PDF Abstract BibTeX arXiv:1910.12181

Code (1)

Luodian/MADAN 공식 구현 pytorch

Tasks

Autonomous Driving Domain Adaptation Segmentation Semantic Segmentation

Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation

2021-03-08 · CVPR 2021 1 · Jianzhong He, Xu Jia, Shuaijun Chen, Jianzhuang Liu

Multi-source unsupervised domain adaptation~(MSDA) aims at adapting models trained on multiple labeled source domains to an unlabeled target domain. In this paper, we propose a novel multi-source domain adaptation framew…

Domain Adaptation Multi-Source Unsupervised Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers

2023-05-23 · Giulia Rizzoli, Donald Shenaj, Pietro Zanuttigh

With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest. However, ground truth data for semantic segmentation is burdensome to provide,…

Domain Adaptation Segmentation Semantic Segmentation Source-Free Domain Adaptation+1

Union-set Multi-source Model Adaptation for Semantic Segmentation

2022-12-06 · Zongyao Li, Ren Togo, Takahiro Ogawa, Miki Haseyama

This paper solves a generalized version of the problem of multi-source model adaptation for semantic segmentation. Model adaptation is proposed as a new domain adaptation problem which requires access to a pre-trained mo…

Domain Adaptation Semantic Segmentation

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation

2021-07-21 · Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free dom…

Domain Adaptation Segmentation Semantic Segmentation Source-Free Domain Adaptation

StandardGAN: Multi-source Domain Adaptation for Semantic Segmentation of Very High Resolution Satellite Images by Data Standardization

2020-04-14 · Onur Tasar, Yuliya Tarabalka, Alain Giros, Pierre Alliez 외

Domain adaptation for semantic segmentation has recently been actively studied to increase the generalization capabilities of deep learning models. The vast majority of the domain adaptation methods tackle single-source …

Domain Adaptation Segmentation Semantic Segmentation