본문

서브메뉴

Reducing Label Dependence in Animal Behavior Modeling: Diverse Supervision Strategies for Improved Generalization
Reducing Label Dependence in Animal Behavior Modeling: Diverse Supervision Strategies for ...
Reducing Label Dependence in Animal Behavior Modeling: Diverse Supervision Strategies for Improved Generalization

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202105001
ISBN  
9798290925998
DDC  
310
저자명  
Blau, Ari.
서명/저자  
Reducing Label Dependence in Animal Behavior Modeling: Diverse Supervision Strategies for Improved Generalization
발행사항  
[Sl] : Columbia University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
165 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
주기사항  
Advisor: Paninski, Liam.
학위논문주기  
Thesis (Ph.D.)--Columbia University, 2025.
초록/해제  
요약Understanding and modeling animal behavior is a central goal in behavioral neuroscience and computational ethology. With advances in imaging and tracking technologies, the field has entered a new era of high-dimensional spatiotemporal data. However, the ability to provide high-quality labels has not-and inherently cannot-scale at the same pace. This growing gap underscores the need for diverse forms of supervision to extract meaningful insights from increasingly complex behavioral datasets. This dissertation presents a series of computational frameworks for representing and segmenting animal behavior, progressing from pose estimation to structured temporal modeling, with a focus on leveraging supervised, semi-supervised, and unsupervised methods. The first part of this dissertation focuses on semi-supervised keypoint estimation in multi-animal settings. In Chapter 2, we introduce SemiMultiPose, a semi-supervised model for multi-animal pose estimation that combines supervised keypoint annotations with unsupervised losses on unlabeled video data. By leveraging the structure inherent in pose-based representations, this framework extracts meaningful intermediate features from raw video, even in the absence of dense labels. This approach enables reduced supervision requirements and improved generalization in complex behavioral settings, demonstrating the value of incorporating unlabeled frames into the training process.Chapter 3 presents a comparative analysis of action segmentation frameworks under different supervision regimes. Action segmentation involves classifying discrete animal behaviors over time based on spatiotemporal features extracted from video. We evaluate supervised, unsupervised, and semi-supervised methods on multiple benchmark datasets, highlighting their trade-offs in performance, data efficiency, and interpretability. This study underscores the importance of temporal structure and representation learning in developing scalable, accurate models of behavior.The third part of the dissertation, presented in Chapter 4, focuses on transformer-based behavior segmentation. We adapt vision transformers (ViTs) for behavioral video analysis by first extracting unsupervised frame-level representations from raw video using a pretrained ViT backbone. These embeddings are then used as inputs for action segmentation models, leveraging the temporal modeling tools developed in Chapter 3. We also explore combining these video-derived features with structured pose representations to improve segmentation performance. This work, part of a collaborative project, demonstrates the effectiveness of ViT backbones in segmenting behavior from both raw video and pose data.Chapter 5 turns to the problem of encoding behavior into neural activity. Building on the representations developed in earlier chapters-continuous kinematic features from Chapter 2 and discrete behavioral states from Chapter 3-we examine how these different forms of behavioral abstraction are reflected in neural population activity. We develop and evaluate encoder models that map these distinct behavioral representations into neural space, with a focus on how the structure of the input-symbolic versus metric-shapes the geometry, predictability, and biological interpretability of the resulting neural codes.Together, these chapters address the central challenge of extracting meaningful insights from large volumes of high-dimensional spatiotemporal data. By developing behavior modeling methods under varying levels of supervision, this work shows how structured representations can emerge even when labeled data are limited. Finally, neural encoding models provide a framework for probing how these learned representations-both continuous and discrete-are reflected in neural activity, offering a principled lens into the brain-behavior relationship.
일반주제명  
Statistics
일반주제명  
Neurosciences
일반주제명  
Behavioral sciences
키워드  
Behavioral neuroscience
키워드  
Computer vision
키워드  
Machine learning
키워드  
Semi-supervised learning
키워드  
Animal behavior
기타저자  
Columbia University Statistics
기본자료저록  
Dissertations Abstracts International. 87-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359284
■00520260202105001
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290925998
■035    ▼a(MiAaPQ)AAI32165004
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a310
■1001  ▼aBlau,  Ari.
■24510▼aReducing  Label  Dependence  in  Animal  Behavior  Modeling:  Diverse  Supervision  Strategies  for  Improved  Generalization
■260    ▼a[Sl]▼bColumbia  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a165  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-02,  Section:  B.
■500    ▼aAdvisor:  Paninski,  Liam.
■5021  ▼aThesis  (Ph.D.)--Columbia  University,  2025.
■520    ▼aUnderstanding  and  modeling  animal  behavior  is  a  central  goal  in  behavioral  neuroscience  and  computational  ethology.  With  advances  in  imaging  and  tracking  technologies,  the  field  has  entered  a  new  era  of  high-dimensional  spatiotemporal  data.  However,  the  ability  to  provide  high-quality  labels  has  not-and  inherently  cannot-scale  at  the  same  pace.  This  growing  gap  underscores  the  need  for  diverse  forms  of  supervision  to  extract  meaningful  insights  from  increasingly  complex  behavioral  datasets.  This  dissertation  presents  a  series  of  computational  frameworks  for  representing  and  segmenting  animal  behavior,  progressing  from  pose  estimation  to  structured  temporal  modeling,  with  a  focus  on  leveraging  supervised,  semi-supervised,  and  unsupervised  methods. The  first  part  of  this  dissertation  focuses  on  semi-supervised  keypoint  estimation  in  multi-animal  settings.  In  Chapter  2,  we  introduce  SemiMultiPose,  a  semi-supervised  model  for  multi-animal  pose  estimation  that  combines  supervised  keypoint  annotations  with  unsupervised  losses  on  unlabeled  video  data.  By  leveraging  the  structure  inherent  in  pose-based  representations,  this  framework  extracts  meaningful  intermediate  features  from  raw  video,  even  in  the  absence  of  dense  labels.  This  approach  enables  reduced  supervision  requirements  and  improved  generalization  in  complex  behavioral  settings,  demonstrating  the  value  of  incorporating  unlabeled  frames  into  the  training  process.Chapter  3  presents  a  comparative  analysis  of  action  segmentation  frameworks  under  different  supervision  regimes.  Action  segmentation  involves  classifying  discrete  animal  behaviors  over  time  based  on  spatiotemporal  features  extracted  from  video.  We  evaluate  supervised,  unsupervised,  and  semi-supervised  methods  on  multiple  benchmark  datasets,  highlighting  their  trade-offs  in  performance,  data  efficiency,  and  interpretability.  This  study  underscores  the  importance  of  temporal  structure  and  representation  learning  in  developing  scalable,  accurate  models  of  behavior.The  third  part  of  the  dissertation,  presented  in  Chapter  4,  focuses  on  transformer-based  behavior  segmentation.  We  adapt  vision  transformers  (ViTs)  for  behavioral  video  analysis  by  first  extracting  unsupervised  frame-level  representations  from  raw  video  using  a  pretrained  ViT  backbone.  These  embeddings  are  then  used  as  inputs  for  action  segmentation  models,  leveraging  the  temporal  modeling  tools  developed  in  Chapter  3.  We  also  explore  combining  these  video-derived  features  with  structured  pose  representations  to  improve  segmentation  performance.  This  work,  part  of  a  collaborative  project,  demonstrates  the  effectiveness  of  ViT  backbones  in  segmenting  behavior  from  both  raw  video  and  pose  data.Chapter  5  turns  to  the  problem  of  encoding  behavior  into  neural  activity.  Building  on  the  representations  developed  in  earlier  chapters-continuous  kinematic  features  from  Chapter  2  and  discrete  behavioral  states  from  Chapter  3-we  examine  how  these  different  forms  of  behavioral  abstraction  are  reflected  in  neural  population  activity.  We  develop  and  evaluate  encoder  models  that  map  these  distinct  behavioral  representations  into  neural  space,  with  a  focus  on  how  the  structure  of  the  input-symbolic  versus  metric-shapes  the  geometry,  predictability,  and  biological  interpretability  of  the  resulting  neural  codes.Together,  these  chapters  address  the  central  challenge  of  extracting  meaningful  insights  from  large  volumes  of  high-dimensional  spatiotemporal  data.  By  developing  behavior  modeling  methods  under  varying  levels  of  supervision,  this  work  shows  how  structured  representations  can  emerge  even  when  labeled  data  are  limited.  Finally,  neural  encoding  models  provide  a  framework  for  probing  how  these  learned  representations-both  continuous  and  discrete-are  reflected  in  neural  activity,  offering  a  principled  lens  into  the  brain-behavior  relationship.
■590    ▼aSchool  code:  0054.
■650  4▼aStatistics
■650  4▼aNeurosciences
■650  4▼aBehavioral  sciences
■653    ▼aBehavioral  neuroscience
■653    ▼aComputer  vision
■653    ▼aMachine  learning
■653    ▼aSemi-supervised  learning
■653    ▼aAnimal  behavior
■690    ▼a0463
■690    ▼a0800
■690    ▼a0602
■690    ▼a0317
■71020▼aColumbia  University▼bStatistics.
■7730  ▼tDissertations  Abstracts  International▼g87-02B.
■790    ▼a0054
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359284▼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
    TF15238 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.