Exploring category-agnostic clusters for open-set domain adaptation

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...

Full description

Saved in:
Bibliographic Details
Main Authors: PAN, Yingwei, YAO, Ting, LI, Yehao, NGO, Chong-wah, MEI, Tao
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2020
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6485
https://ink.library.smu.edu.sg/context/sis_research/article/7488/viewcontent/Pan_Exploring_Category_Agnostic_Clusters_for_Open_Set_Domain_Adaptation_CVPR_2020_paper.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-7488
record_format dspace
spelling sg-smu-ink.sis_research-74882022-01-10T05:14:08Z Exploring category-agnostic clusters for open-set domain adaptation PAN, Yingwei YAO, Ting LI, Yehao NGO, Chong-wah MEI, Tao 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 closedset 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 categoryagnostic 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. 2020-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6485 info:doi/10.1109/CVPR42600.2020.01388 https://ink.library.smu.edu.sg/context/sis_research/article/7488/viewcontent/Pan_Exploring_Category_Agnostic_Clusters_for_Open_Set_Domain_Adaptation_CVPR_2020_paper.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computer Sciences Graphics and Human Computer Interfaces
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Computer Sciences
Graphics and Human Computer Interfaces
spellingShingle Computer Sciences
Graphics and Human Computer Interfaces
PAN, Yingwei
YAO, Ting
LI, Yehao
NGO, Chong-wah
MEI, Tao
Exploring category-agnostic clusters for open-set domain adaptation
description 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 closedset 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 categoryagnostic 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.
format text
author PAN, Yingwei
YAO, Ting
LI, Yehao
NGO, Chong-wah
MEI, Tao
author_facet PAN, Yingwei
YAO, Ting
LI, Yehao
NGO, Chong-wah
MEI, Tao
author_sort PAN, Yingwei
title Exploring category-agnostic clusters for open-set domain adaptation
title_short Exploring category-agnostic clusters for open-set domain adaptation
title_full Exploring category-agnostic clusters for open-set domain adaptation
title_fullStr Exploring category-agnostic clusters for open-set domain adaptation
title_full_unstemmed Exploring category-agnostic clusters for open-set domain adaptation
title_sort exploring category-agnostic clusters for open-set domain adaptation
publisher Institutional Knowledge at Singapore Management University
publishDate 2020
url https://ink.library.smu.edu.sg/sis_research/6485
https://ink.library.smu.edu.sg/context/sis_research/article/7488/viewcontent/Pan_Exploring_Category_Agnostic_Clusters_for_Open_Set_Domain_Adaptation_CVPR_2020_paper.pdf
_version_ 1770575973905858560