TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Domain Adaptation	Office-31	Contrastive Adaptation Network	Average Accuracy	90.6	# 6
Domain Adaptation	VisDA2017	CAN	Accuracy	87.2	# 8

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/contrastive-adaptation-network-for/domain-adaptation-on-office-31)](https://paperswithcode.com/sota/domain-adaptation-on-office-31?p=contrastive-adaptation-network-for)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/contrastive-adaptation-network-for/domain-adaptation-on-visda2017)](https://paperswithcode.com/sota/domain-adaptation-on-visda2017?p=contrastive-adaptation-network-for)`

Contrastive Adaptation Network for Unsupervised Domain Adaptation

CVPR 2019 · Guoliang Kang, Lu Jiang, Yi Yang, Alexander G. Hauptmann ·

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.