Instance Adaptive Self-Training for Unsupervised Domain Adaptation
european conference on computer vision, pp. 415-430, 2020.
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
PPT (Upload PPT)