Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning

by   Shengjia Zhang, et al.

By leveraging data from a fully labeled source domain, unsupervised domain adaptation (UDA) improves classification performance on an unlabeled target domain through explicit discrepancy minimization of data distribution or adversarial learning. As an enhancement, category alignment is involved during adaptation to reinforce target feature discrimination by utilizing model prediction. However, there remain unexplored problems about pseudo-label inaccuracy incurred by wrong category predictions on target domain, and distribution deviation caused by overfitting on source domain. In this paper, we propose a model-agnostic two-stage learning framework, which greatly reduces flawed model predictions using soft pseudo-label strategy and avoids overfitting on source domain with a curriculum learning strategy. Theoretically, it successfully decreases the combined risk in the upper bound of expected error on the target domain. At the first stage, we train a model with distribution alignment-based UDA method to obtain soft semantic label on target domain with rather high confidence. To avoid overfitting on source domain, at the second stage, we propose a curriculum learning strategy to adaptively control the weighting between losses from the two domains so that the focus of the training stage is gradually shifted from source distribution to target distribution with prediction confidence boosted on the target domain. Extensive experiments on two well-known benchmark datasets validate the universal effectiveness of our proposed framework on promoting the performance of the top-ranked UDA algorithms and demonstrate its consistent superior performance.


page 1

page 2

page 3

page 4


Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access...

Progressive Feature Alignment for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) transfers knowledge from a label-ri...

A Simple Baseline for Adversarial Domain Adaptation-based Unsupervised Flood Forecasting

Flood disasters cause enormous social and economic losses. However, both...

Dynamic Weighted Learning for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) aims to improve the classification ...

Unsupervised Domain Adaptation via Domain-Adaptive Diffusion

Unsupervised Domain Adaptation (UDA) is quite challenging due to the lar...

Unsupervised Domain Adaptation via Discriminative Manifold Propagation

Unsupervised domain adaptation is effective in leveraging rich informati...

Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation

In this paper we address multi-target domain adaptation (MTDA), where gi...

Please sign up or login with your details

Forgot password? Click here to reset