DeepAI AI Chat
Log In Sign Up

Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation

by   Chuang Zhu, et al.
Beijing University of Posts and Telecommunications
Peking University

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing the scalability and performance. In this paper, we propose a hard-aware instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality and diversity of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. We further enrich the hard class pseudo-labels with inter-image information through a skillfully designed hard-aware pseudo-label augmentation. Besides, we propose the region-adaptive regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. For the non-pseudo-label region, consistency constraint is also constructed to introduce stronger supervision signals during model optimization. Our method is so concise and efficient that it is easy to be generalized to other UDA methods. Experiments on GTA5 to Cityscapes, SYNTHIA to Cityscapes, and Cityscapes to Oxford RobotCar demonstrate the superior performance of our approach compared with the state-of-the-art methods.


page 2

page 5

page 10

page 11

page 15


Instance Adaptive Self-Training for Unsupervised Domain Adaptation

The divergence between labeled training data and unlabeled testing data ...

Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training

Recent deep networks achieved state of the art performance on a variety ...

Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint

Recent advances in unsupervised domain adaptation have seen considerable...

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Panoptic segmentation unifies semantic segmentation and instance segment...

SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation

Many existing approaches for unsupervised domain adaptation (UDA) focus ...

IDPL: Intra-subdomain adaptation adversarial learning segmentation method based on Dynamic Pseudo Labels

Unsupervised domain adaptation(UDA) has been applied to image semantic s...