DeepAI AI Chat
Log In Sign Up

Learning Factorized Representations for Open-set Domain Adaptation

by   Mahsa Baktashmotlagh, et al.

Domain adaptation for visual recognition has undergone great progress in the past few years. Nevertheless, most existing methods work in the so-called closed-set scenario, assuming that the classes depicted by the target images are exactly the same as those of the source domain. In this paper, we tackle the more challenging, yet more realistic case of open-set domain adaptation, where new, unknown classes can be present in the target data. While, in the unsupervised scenario, one cannot expect to be able to identify each specific new class, we aim to automatically detect which samples belong to these new classes and discard them from the recognition process. To this end, we rely on the intuition that the source and target samples depicting the known classes can be generated by a shared subspace, whereas the target samples from unknown classes come from a different, private subspace. We therefore introduce a framework that factorizes the data into shared and private parts, while encouraging the shared representation to be discriminative. Our experiments on standard benchmarks evidence that our approach significantly outperforms the state-of-the-art in open-set domain adaptation.


page 1

page 2

page 3

page 4


Progressive Graph Learning for Open-Set Domain Adaptation

Domain shift is a fundamental problem in visual recognition which typica...

Simplifying Open-Set Video Domain Adaptation with Contrastive Learning

In an effort to reduce annotation costs in action recognition, unsupervi...

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

Open Set Domain Adaptation (OSDA) bridges the domain gap between a label...

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

Vision systems trained in closed-world scenarios will inevitably fail wh...

Known-class Aware Self-ensemble for Open Set Domain Adaptation

Existing domain adaptation methods generally assume different domains ha...

Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation

Unsupervised domain adaptation has received significant attention in rec...

Attract or Distract: Exploit the Margin of Open Set

Open set domain adaptation aims to diminish the domain shift across doma...