[1909.03442] CUDA: Contradistinguisher for Unsupervised Domain Adaptation

In this paper, we propose a simple model referred as Contradistinguisher (CTDR) for unsupervised domain adaptation whose objective is to jointly learn to contradistinguish on unlabeled target domain in a fully unsupervised manner along with prior knowledge acquired by supervised learning on an entirely different domain. Most recent works in domain adaptation rely on an indirect way of first aligning the source and target domain distributions and then learn a classifier on a labeled source domain to classify target domain. This approach of an indirect way of addressing the real task of unlabeled target domain classification has three main drawbacks. (i) The sub-task of obtaining a perfect alignment of the domain in itself might be impossible due to large domain shift (e.g., language domains). (ii) The use of multiple classifiers to align the distributions unnecessarily increases the complexity of the neural networks leading to over-fitting in many cases. (iii) Due to distribution alignm

Date: 2019/09/13 12:50

Related Entries

Read more [DL輪読会] “Asymmetric Tri-training for Unsupervised Domain Adaptation (…
0 users, 0 mentions 2018/05/13 10:37
Read more VisDA2018: Visual Domain Adaptation Challenge
0 users, 0 mentions 2018/04/25 00:42
Read more CVPR2019 survey Domain Adaptation on Semantic Segmentation
0 users, 1 mentions 2019/04/23 11:15
Read more Learning Semantic Representations for Unsupervised Domain Adaptation …
0 users, 0 mentions 2018/07/28 06:23
Read more Domain Adaptation 発展と動向まとめ(サーベイ資料)
1 users, 1 mentions 2019/11/18 08:21