Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

Abstract

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influence on learning target representations, remains a major challenge. To overcome this issue, we propose a pseudo-labeling curriculum based on a density-based clustering algorithm. Since samples with high density values are more likely to have correct pseudo-labels, we leverage these subsets to train our target network at the early stage, and utilize data subsets with low density values at the later stage. We can progressively improve the capability of our network to generate pseudo-labels, and thus these target samples with pseudo-labels are effective for training our model. Moreover, we present a clustering constraint to enhance the discriminative power of the learned target features. Our approach achieves state-of-the-art performance on three benchmarks: Office-31, imageCLEF-DA, and Office-Home.

Accepted to British Machine Vision Conference (BMVC) 2019

References in corpus (9)

• Learning Transferable Features with Deep Adaptation Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Domain Separation Networks
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Active Self-Paced Learning for Cost-Effective and Progressive Face Identification

Cited by in corpus (13)

• Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation
• CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
• Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems
• Adversarial Domain Adaptation with Prototype-Based Normalized Output Conditioner
• Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
• A Survey on Curriculum Learning
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• Cross-Domain Gradient Discrepancy Minimization for Unsupervised Domain Adaptation
• A Sample Selection Approach for Universal Domain Adaptation
• Synthetic-to-Real Unsupervised Domain Adaptation for Scene Text Detection in the Wild
• On-target Adaptation