Consistency Regularization for Domain Adaptation

2022-08-23 · Kian Boon Koh, Basura Fernando

Collection of real world annotations for training semantic segmentation models is an expensive process. Unsupervised domain adaptation (UDA) tries to solve this problem by studying how more accessible data such as synthetic data can be used to train and adapt models to real world images without requiring their annotations. Recent UDA methods applies self-learning by training on pixel-wise classification loss using a student and teacher network. In this paper, we propose the addition of a consistency regularization term to semi-supervised UDA by modelling the inter-pixel relationship between elements in networks' output. We demonstrate the effectiveness of the proposed consistency regularization term by applying it to the state-of-the-art DAFormer framework and improving mIoU19 performance on the GTA5 to Cityscapes benchmark by 0.8 and mIou16 performance on the SYNTHIA to Cityscapes benchmark by 1.2.

📄 PDF Abstract BibTeX arXiv:2208.11084

Code (1)

kw01sg/crda 공식 구현 pytorch

Tasks

Domain AdaptationSelf-LearningSemantic Segmentation Unsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Self-Learning 설명 없음

Text-Driven Generative Domain Adaptation with Spectral Consistency Regularization

2023-01-01 · ICCV 2023 1 · Zhenhuan Liu, Liang Li, Jiayu Xiao, Zheng-Jun Zha 외

Combined with the generative prior of pre-trained models and the flexibility of text, text-driven generative domain adaptation can generate images from a wide range of target domains. However, current methods still s…

Diversity Domain Adaptation

Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation

2020-09-18 · Kaihong Wang, Chenhongyi Yang, Margrit Betke

Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approaches try to generate images or features mi…

Domain Adaptation Semantic Segmentation Style Transfer Unsupervised Domain Adaptation

Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification

2021-06-16 · Zhipeng Luo, Xiaobing Zhang, Shijian Lu, Shuai Yi

Deep learning-based multi-source unsupervised domain adaptation (MUDA) has been actively studied in recent years. Compared with single-source unsupervised domain adaptation (SUDA), domain shift in MUDA exists not only be…

Classification Domain Adaptation Multi-Source Unsupervised Domain Adaptation Pseudo Label+1

Order-preserving Consistency Regularization for Domain Adaptation and Generalization

2023-09-23 · ICCV 2023 1 · Mengmeng Jing, XianTong Zhen, Jingjing Li, Cees Snoek

Deep learning models fail on cross-domain challenges if the model is oversensitive to domain-specific attributes, e.g., lightning, background, camera angle, etc. To alleviate this problem, data augmentation coupled with …

Data Augmentation Domain Adaptation Optical Character Recognition (OCR)

Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation

2020-04-19 · Qianyu Zhou, Zhengyang Feng, Qiqi Gu, Guangliang Cheng 외

Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from eithe…

Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation