Transporting causal mechanisms for unsupervised domain adaptation

Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the fea...

Full description

Saved in:
Bibliographic Details
Main Authors: YUE, Zhongqi, SUN, Qianru, HUA, Xian-Sheng, ZHANG, Hanwang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2021
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/6229
https://ink.library.smu.edu.sg/context/sis_research/article/7232/viewcontent/ICCV_transport_causal_mechanisms_uda__2_.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-7232
record_format dspace
spelling sg-smu-ink.sis_research-72322021-10-22T05:57:33Z Transporting causal mechanisms for unsupervised domain adaptation YUE, Zhongqi SUN, Qianru HUA, Xian-Sheng ZHANG, Hanwang Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the feature will inevitably lose nondiscriminative semantics in source domain, which is however discriminative in target domain. We use a causal view—transportability theory [41]—to identify that such loss is in fact a confounding effect, which can only be removed by causal intervention. However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap. To this end, we propose a practical solution: Transporting Causal Mechanisms (TCM), to identify the confounder stratum and representations by using the domain-invariant disentangled causal mechanisms, which are discovered in an unsupervised fashion. Our TCM is both theoretically and empirically grounded. Extensive experiments show that TCM achieves state-of-theart performance on three challenging UDA benchmarks: ImageCLEF-DA, Office-Home, and VisDA-2017. Codes are available at https://github.com/yue-zhongqi/ tcm. 2021-10-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/6229 https://ink.library.smu.edu.sg/context/sis_research/article/7232/viewcontent/ICCV_transport_causal_mechanisms_uda__2_.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 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 Graphics and Human Computer Interfaces
spellingShingle Graphics and Human Computer Interfaces
YUE, Zhongqi
SUN, Qianru
HUA, Xian-Sheng
ZHANG, Hanwang
Transporting causal mechanisms for unsupervised domain adaptation
description Existing Unsupervised Domain Adaptation (UDA) literature adopts the covariate shift and conditional shift assumptions, which essentially encourage models to learn common features across domains. However, due to the lack of supervision in the target domain, they suffer from the semantic loss: the feature will inevitably lose nondiscriminative semantics in source domain, which is however discriminative in target domain. We use a causal view—transportability theory [41]—to identify that such loss is in fact a confounding effect, which can only be removed by causal intervention. However, the theoretical solution provided by transportability is far from practical for UDA, because it requires the stratification and representation of the unobserved confounder that is the cause of the domain gap. To this end, we propose a practical solution: Transporting Causal Mechanisms (TCM), to identify the confounder stratum and representations by using the domain-invariant disentangled causal mechanisms, which are discovered in an unsupervised fashion. Our TCM is both theoretically and empirically grounded. Extensive experiments show that TCM achieves state-of-theart performance on three challenging UDA benchmarks: ImageCLEF-DA, Office-Home, and VisDA-2017. Codes are available at https://github.com/yue-zhongqi/ tcm.
format text
author YUE, Zhongqi
SUN, Qianru
HUA, Xian-Sheng
ZHANG, Hanwang
author_facet YUE, Zhongqi
SUN, Qianru
HUA, Xian-Sheng
ZHANG, Hanwang
author_sort YUE, Zhongqi
title Transporting causal mechanisms for unsupervised domain adaptation
title_short Transporting causal mechanisms for unsupervised domain adaptation
title_full Transporting causal mechanisms for unsupervised domain adaptation
title_fullStr Transporting causal mechanisms for unsupervised domain adaptation
title_full_unstemmed Transporting causal mechanisms for unsupervised domain adaptation
title_sort transporting causal mechanisms for unsupervised domain adaptation
publisher Institutional Knowledge at Singapore Management University
publishDate 2021
url https://ink.library.smu.edu.sg/sis_research/6229
https://ink.library.smu.edu.sg/context/sis_research/article/7232/viewcontent/ICCV_transport_causal_mechanisms_uda__2_.pdf
_version_ 1770575895710400512