TY - GEN
T1 - Energy-constrained self-training for unsupervised domain adaptation
AU - Liu, XiaoFeng
AU - Hu, Bo
AU - Liu, Xiongchang
AU - Lu, Jun
AU - You, Jia
AU - Kong, Lingsheng
N1 - Funding Information:
This work was supported by the Jangsu Youth Programme [SBK2020041180], National Natural Science Foundation of China, Younth Programme [grant number 61705221], NIH [NS061841, NS095986], Fanhan Technology, and Hong Kong Government General Research Fund GRF (Ref. No.152202/14E) are greatly appreciated.
Publisher Copyright:
© 2020 IEEE
PY - 2020
Y1 - 2020
N2 - Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, and 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 the energy function minimization objective. It can be applied as a simple additional regularization. In this framework, it is possible to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. 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.
AB - Unsupervised domain adaptation (UDA) aims to transfer the knowledge on a labeled source domain distribution to perform well on an unlabeled target domain. Recently, the deep self-training involves an iterative process of predicting on the target domain and then taking the confident predictions as hard pseudo-labels for retraining. However, the pseudo-labels are usually unreliable, and 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 the energy function minimization objective. It can be applied as a simple additional regularization. In this framework, it is possible to gain the benefits of the energy-based model, while retaining strong discriminative performance following a plug-and-play fashion. 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.
UR - http://www.scopus.com/inward/record.url?scp=85101018265&partnerID=8YFLogxK
U2 - 10.1109/ICPR48806.2021.9413284
DO - 10.1109/ICPR48806.2021.9413284
M3 - Conference article published in proceeding or book
T3 - Proceedings - International Conference on Pattern Recognition
SP - 7515
EP - 7520
BT - Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
ER -