(A) study on segmentation-guided masked autoencoder learning for optical flow estimation광학 흐름 예측을 위한 영상 분할 유도 기반 마스크 오토인코더 학습 연구

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 5
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisor김문철-
dc.contributor.authorSuh, Taewoo-
dc.contributor.author서태우-
dc.date.accessioned2024-07-30T19:31:47Z-
dc.date.available2024-07-30T19:31:47Z-
dc.date.issued2024-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097269&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/321689-
dc.description학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2024.2,[vi, 45 p. :]-
dc.description.abstractMasked autoencoding (MAE) can be valuable for state-of-the-art optical flow estimation models. FlowFormer++ introduced Masked Cost Volume Autoencoding (MCVA) to pretrain its transformer-based cost-volume encoder, along with a block-sharing masking strategy to prevent information leakage between highly correlated cost maps of neighboring source pixels. In this thesis, we propose a segment-sharing masking strategy to further suppress masked information leakage and promote the learning of relations between cost maps of source pixels at different semantic regions. We show that our pretraining task accelerates optical flow training and enables more accurate recovery of motion boundaries. We also show that the proposed segment-sharing MCVA is more difficult than the original block-sharing MCVA, and that it indeed facilitates the propagation of information between cost maps of source pixels in different semantic regions.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subject광학 흐름 추정▼a마스크 오토인코더▼a자기지도학습▼a영상 분할▼a트랜스포머-
dc.subjectOptical flow estimation▼aMasked autoencoding▼aSelf-supervision▼aSegmentation▼aTransformer-
dc.title(A) study on segmentation-guided masked autoencoder learning for optical flow estimation-
dc.title.alternative광학 흐름 예측을 위한 영상 분할 유도 기반 마스크 오토인코더 학습 연구-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :전기및전자공학부,-
dc.contributor.alternativeauthorKim, Munchurl-
Appears in Collection
EE-Theses_Master(석사논문)
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