Inter-Domain Mixup for Semi-Supervised Domain Adaptation

Abstract

Semi-supervised domain adaptation (SSDA) aims to bridge source and target domain distributions, with a small number of target labels available, achieving better classification performance than unsupervised domain adaptation (UDA). However, existing SSDA work fails to make full use of label information from both source and target domains for feature alignment across domains, resulting in label mismatch in the label space during model testing. This paper presents a novel SSDA approach, Inter-domain Mixup with Neighborhood Expansion (IDMNE), to tackle this issue. Firstly, we introduce a cross-domain feature alignment strategy, Inter-domain Mixup, that incorporates label information into model adaptation. Specifically, we employ sample-level and manifold-level data mixing to generate compatible training samples. These newly established samples, combined with reliable and actual label information, display diversity and compatibility across domains, while such extra supervision thus facilitates cross-domain feature alignment and mitigates label mismatch. Additionally, we utilize Neighborhood Expansion to leverage high-confidence pseudo-labeled samples in the target domain, diversifying the label information of the target domain and thereby further increasing the performance of the adaptation model. Accordingly, the proposed approach outperforms existing state-of-the-art methods, achieving significant accuracy improvements on popular SSDA benchmarks, including DomainNet, Office-Home, and Office-31.

Publisted to Elsevier PR2024, available at https://www.sciencedirect.com/science/article/pii/S0031320323007203?via%3Dihub

References in corpus (8)

• Deep Residual Correction Network for Partial Domain Adaptation
• Improve Unsupervised Domain Adaptation with Mixup Training
• Adversarial Style Mining for One-Shot Unsupervised Domain Adaptation
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning
• Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation
• Effective Label Propagation for Discriminative Semi-Supervised Domain Adaptation
• XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
• Relaxed Conditional Image Transfer for Semi-supervised Domain Adaptation