DeepAI AI Chat
Log In Sign Up

Instance Adaptive Self-Training for Unsupervised Domain Adaptation

by   Ke Mei, et al.

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 a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on 'GTA5 to Cityscapes' and 'SYNTHIA to Cityscapes' demonstrate the superior performance of our approach compared with the state-of-the-art methods.


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

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

STRUDEL: Self-Training with Uncertainty Dependent Label Refinement across Domains

We propose an unsupervised domain adaptation (UDA) approach for white ma...

Restyling Data: Application to Unsupervised Domain Adaptation

Machine learning is driven by data, yet while their availability is cons...

Domain Adaptive Multiple Instance Learning for Instance-level Prediction of Pathological Images

Pathological image analysis is an important process for detecting abnorm...

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

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