Tackling Partial Domain Adaptation with Self-Supervision

by   Silvia Bucci, et al.
Istituto Italiano di Tecnologia
Politecnico di Torino

Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains. They allow to train reliable models that work over datasets of different nature (photos, paintings etc), but they still struggle when the domains do not share an identical label space. In the partial domain adaptation setting, where the target covers only a subset of the source classes, it is challenging to reduce the domain gap without incurring in negative transfer. Many solutions just keep the standard domain adaptation techniques by adding heuristic sample weighting strategies. In this work we show how the self-supervisory signal obtained from the spatial co-location of patches can be used to define a side task that supports adaptation regardless of the exact label sharing condition across domains. We build over a recent work that introduced a jigsaw puzzle task for domain generalization: we describe how to reformulate this approach for partial domain adaptation and we show how it boosts existing adaptive solutions when combined with them. The obtained experimental results on three datasets supports the effectiveness of our approach.


page 1

page 2

page 3

page 4


Importance Weighted Adversarial Nets for Partial Domain Adaptation

This paper proposes an importance weighted adversarial nets-based method...

Learning to Transfer Examples for Partial Domain Adaptation

Domain adaptation is critical for learning in new and unseen environment...

Efficient Hierarchical Domain Adaptation for Pretrained Language Models

Generative language models are trained on diverse, general domain corpor...

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

The standard closed-set domain adaptation approaches seek to mitigate di...

Relighting Humans in the Wild: Monocular Full-Body Human Relighting with Domain Adaptation

The modern supervised approaches for human image relighting rely on trai...

Domain Adaptation Through Task Distillation

Deep networks devour millions of precisely annotated images to build the...

Please sign up or login with your details

Forgot password? Click here to reset