2021/03/22 by Ni Xiao, Lei Zhang, Xiao, Ni +1 · 6 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #cs.LG
paper · pdf · doi:10.48550/arxiv.2103.13814
This paper has been accepted by CVPR2021
arxiv created 2021/03/22 · openalex publication_date 2021/03/22 · arxiv updated 2021/03/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Unsupervised domain adaptation (UDA) aims to improve the classification performance on an unlabeled target domain by leveraging information from a fully labeled source domain. Recent approaches explore domain-invariant and class-discriminant representations to tackle this task. These methods, however, ignore the interaction between domain alignment learning and class discrimination learning. As a result, the missing or inadequate tradeoff between domain alignment and class discrimination are prone to the problem of negative transfer. In this paper, we propose Dynamic Weighted Learning (DWL) to avoid the discriminability vanishing problem caused by excessive alignment learning and domain misalignment problem caused by excessive discriminant learning. Technically, DWL dynamically weights the learning losses of alignment and discriminability by introducing the degree of alignment and discriminability. Besides, the problem of sample imbalance across domains is first considered in our work, and we solve the problem by weighing the samples to guarantee information balance across domains. Extensive experiments demonstrate that DWL has an excellent performance in several benchmark datasets.