1. [Publications](/publications)
2. Confidence Regularized Self-Training
 
 # Confidence Regularized Self-Training

  ![](/sites/default/files/styles/wide/public/publications/CRST2.png?itok=K66rSgCb)

 Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident predictions as pseudo-labels for retraining. However, since pseudo-labels can be noisy, self-training can put overconfident label belief on wrong classes, leading to deviated solutions with propagated errors. To address the problem, we propose a confidence regularized self-training (CRST) framework, formulated as regularized self-training. Our method treats pseudo-labels as continuous latent variables jointly optimized via alternating optimization. We propose two types of confidence regularization: label regularization (LR) and model regularization (MR). CRST-LR generates soft pseudo-labels while CRST-MR encourages the smoothness on network output. Extensive experiments on image classification and semantic segmentation show that CRSTs outperform their non-regularized counterpart with state-of-the-art performance. The code and models of this work are available at <https://github.com/yzou2/CRST>.



 ## Authors



Yang Zou (CMU)

[Zhiding Yu](/person/zhiding-yu)

Xiaofeng Liu (CMU)

B. V. K. Vijaya Kumar (CMU)

Jinsong Wang (GM)

 

 

 ## Publication Date



Sunday, October 27, 2019

 

 ## Published in



[IEEE/CVF International Conference on Computer Vision (ICCV) 2019 (Oral)](http://iccv2019.thecvf.com/)

 

 ## Research Area



[Computer Vision](/research-area/computer-vision)

[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

 

 

 ## External Links



[Paper (arXiv)](https://arxiv.org/abs/1908.09822)

[Code](https://github.com/yzou2/CRST)

[Talk](https://www.youtube.com/watch?v=xzygVl7ZncQ&t=6m2s)

[Slides](https://chrisding.github.io/publications/ICCV19_Slides.pdf)

[Poster](https://chrisding.github.io/publications/ICCV19_Poster.pdf)

 

 

 ## Copyright



This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to <pubs-permissions@ieee.org>.