Partial Domain Adaptation without Domain Alignment

08/29/2021
by   Weikai Li, et al.
0

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a well-labeled source domain to a different but related unlabeled target domain with identical label space. Currently, the main workhorse for solving UDA is domain alignment, which has proven successful. However, it is often difficult to find an appropriate source domain with identical label space. A more practical scenario is so-called partial domain adaptation (PDA) in which the source label set or space subsumes the target one. Unfortunately, in PDA, due to the existence of the irrelevant categories in the source domain, it is quite hard to obtain a perfect alignment, thus resulting in mode collapse and negative transfer. Although several efforts have been made by down-weighting the irrelevant source categories, the strategies used tend to be burdensome and risky since exactly which irrelevant categories are unknown. These challenges motivate us to find a relatively simpler alternative to solve PDA. To achieve this, we first provide a thorough theoretical analysis, which illustrates that the target risk is bounded by both model smoothness and between-domain discrepancy. Considering the difficulty of perfect alignment in solving PDA, we turn to focus on the model smoothness while discard the riskier domain alignment to enhance the adaptability of the model. Specifically, we instantiate the model smoothness as a quite simple intra-domain structure preserving (IDSP). To our best knowledge, this is the first naive attempt to address the PDA without domain alignment. Finally, our empirical results on multiple benchmark datasets demonstrate that IDSP is not only superior to the PDA SOTAs by a significant margin on some benchmarks (e.g., +10 +8

READ FULL TEXT

page 8

page 10

page 13

research
09/04/2018

Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories

Unsupervised domain adaptation (UDA) aims to learn the unlabeled target ...
research
12/03/2022

Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation

The standard closed-set domain adaptation approaches seek to mitigate di...
research
04/07/2022

Jacobian Norm for Unsupervised Source-Free Domain Adaptation

Unsupervised Source (data) Free domain adaptation (USFDA) aims to transf...
research
04/10/2020

Deep Residual Correction Network for Partial Domain Adaptation

Deep domain adaptation methods have achieved appealing performance by le...
research
08/27/2020

Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation

Partial domain adaptation (PDA) attracts appealing attention as it deals...
research
03/26/2016

Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets

The goal of domain adaptation is to adapt models learned on a source dom...
research
05/06/2021

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) considers that the target domain conta...

Please sign up or login with your details

Forgot password? Click here to reset