Addressing distribution shift in computer vision컴퓨터 비전에서 발생하는 분포 변화 완화

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 2
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisor주재걸-
dc.contributor.authorLee, Jungsoo-
dc.contributor.author이정수-
dc.date.accessioned2024-08-08T19:30:58Z-
dc.date.available2024-08-08T19:30:58Z-
dc.date.issued2024-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1098136&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/321981-
dc.description학위논문(박사) - 한국과학기술원 : 김재철AI대학원, 2024.2,[vi, 56 p. :]-
dc.description.abstracthowever, they often suffer from notable performance degradation when confronted with distribution shifts between the train set and the test set. Addressing this challenge without the need for additional data collection has become a recent research focus. A primary hurdle in handling such shifts is the dataset bias, where models overly rely on the unwanted correlation between peripheral attributes and labels. This bias can lead models to learn irrelevant features, hindering their ability to generalize to various data distributions. Another challenge is the domain shift, which encompasses differences in style, object sizes, or sources of datasets. Among various techniques for addressing the domain shift, test-time adaptation (TTA) has gained traction for its practicality in mitigating these shifts. This thesis mainly tackles such two challenges in computer vision and further suggests the future work direction of addressing distribution shifts.-
dc.description.abstractIn computer vision, deep neural networks have made significant progresses-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subject분포 변화▼a견고함▼a편향 완화▼a테스트 시간 적응-
dc.subjectDistribution shift▼aRobustness▼aDebiasing▼aTest-time adaptation-
dc.titleAddressing distribution shift in computer vision-
dc.title.alternative컴퓨터 비전에서 발생하는 분포 변화 완화-
dc.typeThesis(Ph.D)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :김재철AI대학원,-
dc.contributor.alternativeauthorChoo, Jaegul-
Appears in Collection
AI-Theses_Ph.D.(박사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0