Instance Adaptive Self-Training for Unsupervised Domain Adaptation

2020/08/27 by Ke Mei, Chuang Zhu, Mei, Ke +5 · 6 citations
Computer Science · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.2008.12197

openalex publication_date 2020/08/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The divergence between labeled training data and unlabeled testing data is a significant challenge for recent deep learning models. Unsupervised domain adaptation (UDA) attempts to solve such a problem. Recent works show that self-training is a powerful approach to UDA. However, existing methods have difficulty in balancing scalability and performance. In this paper, we propose an instance adaptive self-training framework for UDA on the task of semantic segmentation. To effectively improve the quality of pseudo-labels, we develop a novel pseudo-label generation strategy with an instance adaptive selector. Besides, we propose the region-guided regularization to smooth the pseudo-label region and sharpen the non-pseudo-label region. Our method is so concise and efficient that it is easy to be generalized to other unsupervised domain adaptation methods. Experiments on 'GTA5 to Cityscapes' and 'SYNTHIA to Cityscapes' demonstrate the superior performance of our approach compared with the state-of-the-art methods.

Citations

• ImageNet classification with deep convolutional neural networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in\n Semantic Segmentation

Cited by

• Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
• Instance-Aware Test-Time Segmentation for Continual Domain Shifts
• Navigating the Wild: Pareto-Optimal Visual Decision-Making in Image Space
• FRIEREN: Federated Learning with Vision-Language Regularization for Segmentation
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation
• Multi-Prompt Progressive Alignment for Multi-Source Unsupervised Domain Adaptation

Related

• Hard-aware Instance Adaptive Self-training for Unsupervised Cross-domain Semantic Segmentation
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinement
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation
• Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training