Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation

By Yiyang Zhang, Feng Liu, Zhen Fang, Bo Yuan, Guangquan Zhang, Jie Lu. 2020

33 citations recorded by the source corpus.

In unsupervised domain adaptation (UDA), classifiers for the target domain are trained with massive true-label data from the source domain and unlabeled data from the target domain. However, it may be difficult to collect fully-true-label data in a source domain given limited budget. To mitigate this problem, we consider a novel problem setting where the classifier for the target domain has to be trained with complementary-label data from the source domain and unlabeled data from the target domain named budget-friendly UDA (BFUDA). The key benefit is that it is much less costly to collect complementary-label source data (required by BFUDA) than collecting the true-label source data (required by ordinary UDA). To this end, complementary label adversarial network (CLARINET) is proposed to solve the BFUDA problem. CLARINET maintains two deep networks simultaneously, where one focuses on classifying complementary-label source data and the other takes care of the source-to-target distributional adaptation. Experiments show that CLARINET significantly outperforms a series of competent baselines.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhen Fang
2. Gan Sun
3. Xiao Wang
4. Yang Cong
5. Lixu Wang
6. Qi Zhu
7. Zhengming Ding
8. Shichao Xu

Citations in the corpus

• Federated Class-Incremental Learning (2022, background): “[34] integrates unsupervised domain adaptation [5, 9, 27, 28, 57] into federated learning framework [14, 31].”
• Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation (2021, background): “Using such domain-invariant knowledge, they can learn effective pixel-level classifiers that have good prediction performance on the unlabeled target domain [9], [10], [32], [49].”