Curation Bias in Domain Adaptation

Simple item page
dc.contributor.advisorPirsiavash, Hamed
dc.contributor.authorTejankar, Ajinkya Baban
dc.contributor.departmentComputer Science and Electrical Engineering
dc.contributor.programComputer Science
dc.date.accessioned2021-09-01T13:55:29Z
dc.date.available2021-09-01T13:55:29Z
dc.date.issued2020-01-20
dc.description.abstractDomain adaptation is an important problem with many practical applications. The goal is to adapt a model trained on one domain (source) to another domain (target) with scarce or no annotation. We observe that the unlabeled target datasets of popular domain adaptation benchmarks do not contain any categories apart from testing categories. We believe this introduces a bias that does not exist in many practical applications. We note that this bias can be reduced easily by appending the datasets with images from non-testing categories. On these modified benchmarks, state-of-the-art domain adaptation methods show a large drop in performance. Thus, raising concerns about their practical applicability. Further, we show that a simple, two-stage method involving self-supervised task of rotation prediction and knowledge distillation is a competitive baseline.
dc.formatapplication:pdf
dc.genretheses
dc.identifierdoi:10.13016/m2rgst-rw9k
dc.identifier.other12265
dc.identifier.urihttp://hdl.handle.net/11603/22847
dc.languageen
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Theses and Dissertations Collection
dc.relation.ispartofUMBC Graduate School Collection
dc.relation.ispartofUMBC Student Collection
dc.sourceOriginal File Name: Tejankar_umbc_0434M_12265.pdf
dc.titleCuration Bias in Domain Adaptation
dc.typeText
dcterms.accessRightsDistribution Rights granted to UMBC by the author.
dcterms.accessRightsThis item may be protected under Title 17 of the U.S. Copyright Law. It is made available by UMBC for non-commercial research and education. For permission to publish or reproduce, please see http://aok.lib.umbc.edu/specoll/repro.php or contact Special Collections at speccoll(at)umbc.edu

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Tejankar_umbc_0434M_12265.pdf
Size:
8.68 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Tejankar-Ajinkya Baban_Open.pdf
Size:
1.48 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

UMBC Theses and Dissertations
UMBC Computer Science and Electrical Engineering Department
UMBC Graduate School
UMBC Student Collection