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

TL;DR

This paper introduces a two-stage, model-agnostic framework for unsupervised domain adaptation that reduces pseudo-label errors and overfitting, significantly improving target domain classification performance.

Contribution

It proposes a novel soft pseudo-label strategy combined with curriculum learning to enhance UDA, reducing prediction errors and overfitting, with theoretical guarantees and extensive empirical validation.

Findings

Significant performance improvements on benchmark datasets.

Universal effectiveness across top-ranked UDA algorithms.

Consistent superior results demonstrating robustness.

Abstract

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.