Part-guide teaching: part-guide pseudo-label self refinement for unsupervised person re-identification비지도 사람 재식별을 위한 부분 지도 의사 레이블 자가 정제

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 1497
  • Download : 0
Unsupervised person re-identification (re-ID) aims to retrieve the same person across different camera-views for a given query without any labels. Recently, state-of-the-art methods that leverage pseudo-labels through clustering achieved competitive results. Despite improvements from the above methods, unreliable clusters and noisy pseudo-labels have remained problems. In this work, we propose Part-Guide Teaching (PGT) framework that effectively utilizes part-local features to address these problems. The proposed framework performs robust clustering based on part-wise relationships and refines hard pseudo-labels by guidance from part-local feature classifiers. Our refinement process works online in a self-teaching manner, which does not require additional teacher networks that need a high computational cost in the training stage. Experiment on Market-1501 and DukeMTMC-reID demonstrates the superiority of the proposed methods.
Advisors
Yoon, Sung-Euiresearcher윤성의researcher
Description
한국과학기술원 :전산학부,
Publisher
한국과학기술원
Issue Date
2021
Identifier
325007
Language
eng
Description

학위논문(석사) - 한국과학기술원 : 전산학부, 2021.2,[iii, 17 p. :]

Keywords

Person re-identification▼aImage search▼aUnsupervised learning▼aNoisy label; 사람 재인식▼a이미지 검색▼a비지도 학습▼a노이지 레이블

URI
http://hdl.handle.net/10203/296139
Link
http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=948465&flag=dissertation
Appears in Collection
CS-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