Contrastive Adaptation Network for Unsupervised Domain Adaptation

Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. T...

Full description

Saved in:
Bibliographic Details
Published in2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4888 - 4897
Main Authors Kang, Guoliang, Jiang, Lu, Yang, Yi, Hauptmann, Alexander G.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2019
Subjects
Categorization
Deep Learning
Recognition: Detection
Representation Learning
Retrieval
Online AccessGet full text

Cover

More Information
Summary:Unsupervised Domain Adaptation (UDA) makes predictions for the target domain data while manual annotations are only available in the source domain. Previous methods minimize the domain discrepancy neglecting the class information, which may lead to misalignment and poor generalization performance. To address this issue, this paper proposes Contrastive Adaptation Network (CAN) optimizing a new metric which explicitly models the intra-class domain discrepancy and the inter-class domain discrepancy. We design an alternating update strategy for training CAN in an end-to-end manner. Experiments on two real-world benchmarks Office-31 and VisDA-2017 demonstrate that CAN performs favorably against the state-of-the-art methods and produces more discriminative features.
ISSN:2575-7075
DOI:10.1109/CVPR.2019.00503