Inter-Domain Mixup for Semi-Supervised Domain Adaptation
Authors:
- Guanbin LiGLGuanbin Li
Preprint
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.Keywords
All Related Versions
- Version 1, 2024-01-21, ArXiv
- Published version: Pattern Recognition, 146.
This publication has 23 references indexed in Scilit:
- Class-specific and self-learning local manifold structure for domain adaptationPattern Recognition, 2023
- How to Reduce Change Detection to Semantic SegmentationPattern Recognition, 2023
- CrossRectify: Leveraging disagreement for semi-supervised object detectionPattern Recognition, 2022
- Pose-driven attention-guided image generation for person re-IdentificationPattern Recognition, 2022
- Cross-domain structure learning for visual data recognitionPattern Recognition, 2022
- An End-to-end Supervised Domain Adaptation Framework for Cross-Domain Change DetectionPattern Recognition, 2022
- Learning a Weighted Classifier for Conditional Domain AdaptationKnowledge-Based Systems, 2021
- Randaugment: Practical automated data augmentation with a reduced search space2020
- Deep Residual Learning for Image Recognition2016
- Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-ImprovementMachine Learning, 1997