DeepAI AI Chat
Log In Sign Up

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

02/14/2023
by   Chuang Zhu, et al.
Beijing University of Posts and Telecommunications
Tencent
Peking University
1

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.

READ FULL TEXT

page 2

page 5

page 10

page 11

page 15

08/27/2020

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

The divergence between labeled training data and unlabeled testing data ...
10/18/2018

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

Recent deep networks achieved state of the art performance on a variety ...
05/27/2021

Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint

Recent advances in unsupervised domain adaptation have seen considerable...
03/03/2021

Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Panoptic segmentation unifies semantic segmentation and instance segment...
12/21/2020

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

Many existing approaches for unsupervised domain adaptation (UDA) focus ...
10/07/2022

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

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