Your Classifier can Secretly Suffice Multi-Source Domain Adaptation

by   Naveen Venkat, et al.

Multi-Source Domain Adaptation (MSDA) deals with the transfer of task knowledge from multiple labeled source domains to an unlabeled target domain, under a domain-shift. Existing methods aim to minimize this domain-shift using auxiliary distribution alignment objectives. In this work, we present a different perspective to MSDA wherein deep models are observed to implicitly align the domains under label supervision. Thus, we aim to utilize implicit alignment without additional training objectives to perform adaptation. To this end, we use pseudo-labeled target samples and enforce a classifier agreement on the pseudo-labels, a process called Self-supervised Implicit Alignment (SImpAl). We find that SImpAl readily works even under category-shift among the source domains. Further, we propose classifier agreement as a cue to determine the training convergence, resulting in a simple training algorithm. We provide a thorough evaluation of our approach on five benchmarks, along with detailed insights into each component of our approach.


Generation, augmentation, and alignment: A pseudo-source domain based method for source-free domain adaptation

Conventional unsupervised domain adaptation (UDA) methods need to access...

Combating Domain Shift with Self-Taught Labeling

We present a novel method to combat domain shift when adapting classific...

Unsupervised Domain Adaptation through Self-Supervision

This paper addresses unsupervised domain adaptation, the setting where l...

Algorithm-Dependent Bounds for Representation Learning of Multi-Source Domain Adaptation

We use information-theoretic tools to derive a novel analysis of Multi-s...

Graphical Modeling for Multi-Source Domain Adaptation

Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowle...

Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptation

We present an approach for unsupervised domain adaptation—with a strong ...

Pareto Domain Adaptation

Domain adaptation (DA) attempts to transfer the knowledge from a labeled...

Please sign up or login with your details

Forgot password? Click here to reset