Semi-supervised Deep Domain Adaptation via Coupled Neural Networks

Zhengming Ding, Nasser M. Nasrabadi, Yun Fu

Abstract

Domain adaptation is a promising technique when addressing limited or no labeled target data by borrowing well-labeled knowledge from the auxiliary source data. Recently, researchers have exploited multi-layer structures for discriminative feature learning to reduce the domain discrepancy. However, there are limited research efforts on simultaneously building a deep structure and a discriminative classifier over both labeled source and unlabeled target. In this paper, we propose a semi-supervised deep domain adaptation framework, in which the multi-layer feature extractor and a multi-class classifier are jointly learned to benefit from each other. Specifically, we develop a novel semi-supervised class-wise adaptation manner to fight off the conditional distribution mismatch between two domains by assigning a probabilistic label to each target sample, i.e., multiple class labels with different probabilities. Furthermore, a multi-class classifier is simultaneously trained on labeled source and unlabeled target samples in a semi-supervised fashion. In this way, the deep structure can formally alleviate the domain divergence and enhance the feature transferability. Experimental evaluations on several standard cross-domain benchmarks verify the superiority of our proposed approach.
BibTeX
@article{ding2018semi,
  author = {Zhengming Ding and Nasser M. Nasrabadi and Yun Fu},
  title = {{Semi-supervised Deep Domain Adaptation via Coupled Neural Networks}},
  journal = {IEEE Trans. Image Process.},
  year = {2018},
  url = {https://openreview.net/forum?id=gEY1IGwMJ0},
}

Loading related content...

Figure