본문

서브메뉴

Learning Pose and State-Invariant Object Representations for Fine-Grained Recognition and Retrieval
Learning Pose and State-Invariant Object Representations for Fine-Grained Recognition and ...
Learning Pose and State-Invariant Object Representations for Fine-Grained Recognition and Retrieval

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152751
ISBN  
9798342122955
DDC  
375
저자명  
Sarkar, Rohan.
서명/저자  
Learning Pose and State-Invariant Object Representations for Fine-Grained Recognition and Retrieval
발행사항  
[Sl] : Purdue University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
165 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
주기사항  
Advisor: Kak, Avinash.
학위논문주기  
Thesis (Ph.D.)--Purdue University, 2024.
초록/해제  
요약Object Recognition and Retrieval is a fundamental problem in Computer Vision that involves recognizing objects and retrieving similar object images through visual queries. While deep metric learning is commonly employed to learn image embeddings for solving such problems, the representations learned using existing methods are not robust to changes in viewpoint, pose, and object state, especially for fine-grained recognition and retrieval tasks. To overcome these limitations, this dissertation aims to learn robust object representations that remain invariant to such transformations for fine-grained tasks. First, it focuses on learning dual pose-invariant embeddings to facilitate recognition and retrieval at both the category and finer object-identity levels by learning category and object-identity specific representations in separate embedding spaces simultaneously. For this, the PiRO framework is introduced that utilizes an attention-based dual encoder architecture and novel pose-invariant ranking losses for each embedding space to disentangle the category and object representations while learning pose-invariant features. Second, the dissertation introduces ranking losses that cluster multi-view images of an object together in both the embedding spaces while simultaneously pulling the embeddings of two objects from the same category closer in the category embedding space to learn fundamental category-specific attributes and pushing them apart in the object embedding space to learn discriminative features to distinguish between them. Third, the dissertation addresses state-invariance and introduces a novel Objects: With State: Change dataset to facilitate research in recognizing fine-grained objects with state changes involving structural transformations in addition to pose and viewpoint changes. Fourth, it proposes a curriculum learning strategyto progressively sample object images that are harder to distinguish for training the model, enhancing its ability to capture discriminative features for fine-grained tasks amidst state changes and other transformations. Experimental evaluations demonstrate significant improvements in object recognition and retrieval performance compared to previous methods, validating the effectiveness of the proposed approaches across several challenging datasets under various transformations.
일반주제명  
Curricula
일반주제명  
Object linking & embedding
일반주제명  
Computer science
기타저자  
Purdue University.
기본자료저록  
Dissertations Abstracts International. 86-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163774
■00520250211152751
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798342122955
■035    ▼a(MiAaPQ)AAI31532247
■035    ▼a(MiAaPQ)Purdue26236742
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a375
■1001  ▼aSarkar,  Rohan.
■24510▼aLearning  Pose  and  State-Invariant  Object  Representations  for  Fine-Grained  Recognition  and  Retrieval
■260    ▼a[Sl]▼bPurdue  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a165  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  B.
■500    ▼aAdvisor:  Kak,  Avinash.
■5021  ▼aThesis  (Ph.D.)--Purdue  University,  2024.
■520    ▼aObject  Recognition  and  Retrieval  is  a  fundamental  problem  in  Computer  Vision  that  involves  recognizing  objects  and  retrieving  similar  object  images  through  visual  queries.  While  deep  metric  learning  is  commonly  employed  to  learn  image  embeddings  for  solving  such  problems,  the  representations  learned  using  existing  methods  are  not  robust  to  changes  in  viewpoint,  pose,  and  object  state,  especially  for  fine-grained  recognition  and  retrieval  tasks.  To  overcome  these  limitations,  this  dissertation  aims  to  learn  robust  object  representations  that  remain  invariant  to  such  transformations  for  fine-grained  tasks.  First,  it  focuses  on  learning  dual  pose-invariant  embeddings  to  facilitate  recognition  and  retrieval  at  both  the  category  and  finer  object-identity  levels  by  learning  category  and  object-identity  specific  representations  in  separate  embedding  spaces  simultaneously.  For  this,  the  PiRO  framework  is  introduced  that  utilizes  an  attention-based  dual  encoder  architecture  and  novel  pose-invariant  ranking  losses  for  each  embedding  space  to  disentangle  the  category  and  object  representations  while  learning  pose-invariant  features.  Second,  the  dissertation  introduces  ranking  losses  that  cluster  multi-view  images  of  an  object  together  in  both  the  embedding  spaces  while  simultaneously  pulling  the  embeddings  of  two  objects  from  the  same  category  closer  in  the  category  embedding  space  to  learn  fundamental  category-specific  attributes  and  pushing  them  apart  in  the  object  embedding  space  to  learn  discriminative  features  to  distinguish  between  them.  Third,  the  dissertation  addresses  state-invariance  and  introduces  a  novel  Objects:  With  State:  Change  dataset  to  facilitate  research  in  recognizing  fine-grained  objects  with  state  changes  involving  structural  transformations  in  addition  to  pose  and  viewpoint  changes.  Fourth,  it  proposes  a  curriculum  learning  strategyto  progressively  sample  object  images  that  are  harder  to  distinguish  for  training  the  model,  enhancing  its  ability  to  capture  discriminative  features  for  fine-grained  tasks  amidst  state  changes  and  other  transformations.  Experimental  evaluations  demonstrate  significant  improvements  in  object  recognition  and  retrieval  performance  compared  to  previous  methods,  validating  the  effectiveness  of  the  proposed  approaches  across  several  challenging  datasets  under  various  transformations.
■590    ▼aSchool  code:  0183.
■650  4▼aCurricula
■650  4▼aObject  linking  &  embedding
■650  4▼aComputer  science
■690    ▼a0984
■71020▼aPurdue  University.
■7730  ▼tDissertations  Abstracts  International▼g86-05B.
■790    ▼a0183
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163774▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF13477 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.