CUDA: Contradistinguisher for Unsupervised Domain Adaptation

09/08/2019
by   Sourabh Balgi, et al.
28

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 alignment, the domain-specific information is lost as the domains get morphed. In this work, we propose a simple and direct approach that does not require domain alignment. We jointly learn CTDR on both source and target distribution for unsupervised domain adaptation task using contradistinguish loss for the unlabeled target domain in conjunction with a supervised loss for labeled source domain. Our experiments show that avoiding domain alignment by directly addressing the task of unlabeled target domain classification using CTDR achieves state-of-the-art results on eight visual and four language benchmark domain adaptation datasets.

READ FULL TEXT

page 1

page 6

page 7

page 8

research
05/25/2020

Contradistinguisher: Applying Vapnik's Philosophy to Unsupervised Domain Adaptation

A complex combination of simultaneous supervised-unsupervised learning i...
research
11/17/2018

Deep Discriminative Learning for Unsupervised Domain Adaptation

The primary objective of domain adaptation methods is to transfer knowle...
research
11/24/2017

Unsupervised Domain Adaptation with Similarity Learning

The objective of unsupervised domain adaptation is to leverage features ...
research
09/26/2019

Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where l...
research
11/30/2018

Domain-Invariant Adversarial Learning for Unsupervised Domain Adaption

Unsupervised domain adaption aims to learn a powerful classifier for the...
research
08/11/2020

Learning to Cluster under Domain Shift

While unsupervised domain adaptation methods based on deep architectures...
research
02/21/2017

Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation

The empirical fact that classifiers, trained on given data collections, ...

Please sign up or login with your details

Forgot password? Click here to reset