Instance Adaptive Self-Training for Unsupervised Domain Adaptation

Ke Mei
Ke Mei
Chuang Zhu
Chuang Zhu
Jiaqi Zou
Jiaqi Zou

european conference on computer vision, pp. 415-430, 2020.

Cited by: 0|Views17

Abstract:

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 ...More

Code:

Data:

Your rating :
0

 

Tags
Comments