Cluster Alignment with a Teacher for Unsupervised Domain Adaptation

ICCV 2019 Zhijie DengYucen LuoJun Zhu

Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically learn a domain-invariant representation space to match the marginal distributions of the source and target domains, while ignoring their fine-level structures... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Domain Adaptation ImageCLEF-DA rRevGrad+CAT Accuracy 80.7 # 8
Domain Adaptation MNIST-to-USPS rRevGrad+CAT Accuracy 96 # 7
Domain Adaptation Office-31 rRevGrad+CAT Average Accuracy 80.1 # 20
Domain Adaptation SVNH-to-MNIST rRevGrad+CAT Accuracy 98.8 # 3
Domain Adaptation USPS-to-MNIST MCD+CAT Accuracy 96.3 # 6

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet