Exploring Category-Agnostic Clusters for Open-Set Domain Adaptation

06/11/2020
by   Yingwei Pan, et al.
0

Unsupervised domain adaptation has received significant attention in recent years. Most of existing works tackle the closed-set scenario, assuming that the source and target domains share the exactly same categories. In practice, nevertheless, a target domain often contains samples of classes unseen in source domain (i.e., unknown class). The extension of domain adaptation from closed-set to such open-set situation is not trivial since the target samples in unknown class are not expected to align with the source. In this paper, we address this problem by augmenting the state-of-the-art domain adaptation technique, Self-Ensembling, with category-agnostic clusters in target domain. Specifically, we present Self-Ensembling with Category-agnostic Clusters (SE-CC) – a novel architecture that steers domain adaptation with the additional guidance of category-agnostic clusters that are specific to target domain. These clustering information provides domain-specific visual cues, facilitating the generalization of Self-Ensembling for both closed-set and open-set scenarios. Technically, clustering is firstly performed over all the unlabeled target samples to obtain the category-agnostic clusters, which reveal the underlying data space structure peculiar to target domain. A clustering branch is capitalized on to ensure that the learnt representation preserves such underlying structure by matching the estimated assignment distribution over clusters to the inherent cluster distribution for each target sample. Furthermore, SE-CC enhances the learnt representation with mutual information maximization. Extensive experiments are conducted on Office and VisDA datasets for both open-set and closed-set domain adaptation, and superior results are reported when comparing to the state-of-the-art approaches.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/19/2020

Universal Domain Adaptation through Self Supervision

Unsupervised domain adaptation methods traditionally assume that all sou...
research
12/16/2021

UMAD: Universal Model Adaptation under Domain and Category Shift

Learning to reject unknown samples (not present in the source classes) i...
research
05/31/2018

Learning Factorized Representations for Open-set Domain Adaptation

Domain adaptation for visual recognition has undergone great progress in...
research
11/04/2020

Against Adversarial Learning: Naturally Distinguish Known and Unknown in Open Set Domain Adaptation

Open set domain adaptation refers to the scenario that the target domain...
research
03/08/2020

Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation

Unsupervised domain adaptation aims to leverage labeled data from a sour...
research
05/06/2021

Towards Novel Target Discovery Through Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) considers that the target domain conta...
research
01/31/2023

Domain-Generalizable Multiple-Domain Clustering

Accurately clustering high-dimensional measurements is vital for adequat...

Please sign up or login with your details

Forgot password? Click here to reset