English

Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model

Computer Vision and Pattern Recognition 2022-08-30 v1 Artificial Intelligence Machine Learning Image and Video Processing Signal Processing

Abstract

Deep learning is usually data starved, and the unsupervised domain adaptation (UDA) is developed to introduce the knowledge in the labeled source domain to the unlabeled target domain. Recently, deep self-training presents a powerful means for UDA, involving an iterative process of predicting the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, thus easily leading to deviated solutions with propagated errors. In this paper, we resort to the energy-based model and constrain the training of the unlabeled target sample with an energy function minimization objective. It can be achieved via a simple additional regularization or an energy-based loss. This framework allows us to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. The convergence property and its connection with classification expectation minimization are investigated. We deliver extensive experiments on the most popular and large-scale UDA benchmarks of image classification as well as semantic segmentation to demonstrate its generality and effectiveness.

Keywords

Cite

@article{arxiv.2208.12885,
  title  = {Constraining Pseudo-label in Self-training Unsupervised Domain Adaptation with Energy-based Model},
  author = {Lingsheng Kong and Bo Hu and Xiongchang Liu and Jun Lu and Jane You and Xiaofeng Liu},
  journal= {arXiv preprint arXiv:2208.12885},
  year   = {2022}
}

Comments

International Journal of Intelligent Systems. arXiv admin note: substantial text overlap with arXiv:2101.00316

R2 v1 2026-06-25T02:01:12.369Z