본문

서브메뉴

Representation Learning for Active Perception
Representation Learning for Active Perception
Representation Learning for Active Perception

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260202104841
ISBN  
9798293892471
DDC  
621.3
저자명  
Quenum, Jerome.
서명/저자  
Representation Learning for Active Perception
발행사항  
[Sl] : University of California, Berkeley, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
156 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-04, Section: B.
주기사항  
Advisor: Darrell, Trevor;Malik, Jitendra.
학위논문주기  
Thesis (Ph.D.)--University of California, Berkeley, 2025.
초록/해제  
요약Active perception driven by representation learning lies at the intersection of computer vision and robotics, powered by advanced Artificial Intelligence (AI) algorithms. It has for goal to develop systems that can actively gather information from their environment by learning useful representations to enhance both their perception and decision-making capabilities. This dissertation explores various facets of this topic, with a particular focus on how advanced representation-learning techniques can significantly improve the performance and utility of such systems.We begin by examining the role of precision in AI-driven systems through classical segmentation tasks in Ultra-High-Resolution (UHR) images within the context of battery design. A novel transformer-based network, TransforCNN, is introduced to segment dendrites in Lithium Metal Battery (LMB) 3D X-ray computed tomography (XCT) volumes. This approach significantly improves the accuracy of segmenting critical structures, which is essential for developing more efficient and reliable batteries. The precision gained in this segmentation problem through our proposed representation learning model not only enhances the visual understanding of battery components but also lays the groundwork for more informed and effective design strategies.Building on this foundation, we transition to addressing the challenge of processing Ultra-High-Resolution (UHR) images, which is important for applications requiring both speed and accuracy. We explore this in the context of barcode detection in UHR images, where a new detection pipeline is proposed, integrating a modified Region Proposal Network (RPN) with a proposed segmentation network named Y-Net. This study demonstrates how representation learning can be optimized to reduce latency while maintaining high accuracy, showcasing the potential of AI to handle complex visual tasks in real time.We then examine scalability when it comes to the integration of representation learning for active perception in robotics, where speed, accuracy, adaptability, and robustness are key. Using the Open X Embodiment (OXE) dataset, we investigate a cross-robot self-supervised sensorimotor pre-training approach through RPTx, a multimodal model that does not leverage language instructions and does not use auto-regressive methods. This approach provided valuable insights into the robustness and adaptability issues encountered by robotic systems. Here, we conduct reliability assessments, an examination of negative transfer instances where models struggle to adapt, and we speculate on future directions for overcoming these difficulties. Additionally, we observe that the use of multimodal models that leverage large language models for instruction tuning and that employ auto-regressive techniques led to more stable and promising outcomes with LLARVA, a vision-action instruction tuning paradigm that enhances Robot Learning. These findings demonstrate how learning good representations can enhance robotic systems' ability to interpret and respond to complex environmental cues.Finally, we explore the challenge of extending segmentation models beyond fixed object categories to support reasoning over visual scenes. While current segmentation models work well when objects are clearly defined, they struggle with complex user queries that refer to multiple or implicit objects. Recent work in reasoning segmentation, which generates segmentation masks from natural language input, shows that vision-language models (VLMs) can help address this. However, our experiments show that existing models perform poorly on remote-sensing images, which often contain dense and varied content. To address this, we introduce LISAt, a vision-language model designed to describe remote-sensing images, answer questions about them, and segment objects based on user queries. LISAt is trained on GRES, a dataset with 27,615 annotations across 9,205 images, and PreGRES, a multimodal dataset with over one million question-answer pairs. LISAt outperforms geospatial models like RS-GPT4V by 10.04% in BLEU-4 for image description and improves on open-domain models in reasoning segmentation by 143.36% in generalized Intersection over Union (gIoU). These results show how learning strong multimodal representations can improve scene understanding, especially in the geospatial domain.
일반주제명  
Electrical engineering
일반주제명  
Computer science
일반주제명  
Information technology
키워드  
Active perception
키워드  
Latency optimization
키워드  
Multimodal representations
키워드  
Object detection and segmentation
키워드  
Reasoning segmentation
키워드  
Representation learning
기타저자  
University of California, Berkeley Electrical Engineering & Computer Sciences
기본자료저록  
Dissertations Abstracts International. 87-04B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017359144
■00520260202104841
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798293892471
■035    ▼a(MiAaPQ)AAI32172894
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aQuenum,  Jerome.
■24510▼aRepresentation  Learning  for  Active  Perception
■260    ▼a[Sl]▼bUniversity  of  California,  Berkeley▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a156  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-04,  Section:  B.
■500    ▼aAdvisor:  Darrell,  Trevor;Malik,  Jitendra.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Berkeley,  2025.
■520    ▼aActive  perception  driven  by  representation  learning  lies  at  the  intersection  of  computer  vision  and  robotics,  powered  by  advanced  Artificial  Intelligence  (AI)  algorithms.  It  has  for  goal  to  develop  systems  that  can  actively  gather  information  from  their  environment  by  learning  useful  representations  to  enhance  both  their  perception  and  decision-making  capabilities.  This  dissertation  explores  various  facets  of  this  topic,  with  a  particular  focus  on  how  advanced  representation-learning  techniques  can  significantly  improve  the  performance  and  utility  of  such  systems.We  begin  by  examining  the  role  of  precision  in  AI-driven  systems  through  classical  segmentation  tasks  in  Ultra-High-Resolution  (UHR)  images  within  the  context  of  battery  design.  A  novel  transformer-based  network,  TransforCNN,  is  introduced  to  segment  dendrites  in  Lithium  Metal  Battery  (LMB)  3D  X-ray  computed  tomography  (XCT)  volumes.  This  approach  significantly  improves  the  accuracy  of  segmenting  critical  structures,  which  is  essential  for  developing  more  efficient  and  reliable  batteries.  The  precision  gained  in  this  segmentation  problem  through  our  proposed  representation  learning  model  not  only  enhances  the  visual  understanding  of  battery  components  but  also  lays  the  groundwork  for  more  informed  and  effective  design  strategies.Building  on  this  foundation,  we  transition  to  addressing  the  challenge  of  processing  Ultra-High-Resolution  (UHR)  images,  which  is  important  for  applications  requiring  both  speed  and  accuracy.  We  explore  this  in  the  context  of  barcode  detection  in  UHR  images,  where  a  new  detection  pipeline  is  proposed,  integrating  a  modified  Region  Proposal  Network  (RPN)  with  a  proposed  segmentation  network  named  Y-Net.  This  study  demonstrates  how  representation  learning  can  be  optimized  to  reduce  latency  while  maintaining  high  accuracy,  showcasing  the  potential  of  AI  to  handle  complex  visual  tasks  in  real  time.We  then  examine  scalability  when  it  comes  to  the  integration  of  representation  learning  for  active  perception  in  robotics,  where  speed,  accuracy,  adaptability,  and  robustness  are  key.  Using  the  Open  X  Embodiment  (OXE)  dataset,  we  investigate  a  cross-robot  self-supervised  sensorimotor  pre-training  approach  through  RPTx,  a  multimodal  model  that  does  not  leverage  language  instructions  and  does  not  use  auto-regressive  methods.  This  approach  provided  valuable  insights  into  the  robustness  and  adaptability  issues  encountered  by  robotic  systems.  Here,  we  conduct  reliability  assessments,  an  examination  of  negative  transfer  instances  where  models  struggle  to  adapt,  and  we  speculate  on  future  directions  for  overcoming  these  difficulties.  Additionally,  we  observe  that  the  use  of  multimodal  models  that  leverage  large  language  models  for  instruction  tuning  and  that  employ  auto-regressive  techniques  led  to  more  stable  and  promising  outcomes  with  LLARVA,  a  vision-action  instruction  tuning  paradigm  that  enhances  Robot  Learning.  These  findings  demonstrate  how  learning  good  representations  can  enhance  robotic  systems'  ability  to  interpret  and  respond  to  complex  environmental  cues.Finally,  we  explore  the  challenge  of  extending  segmentation  models  beyond  fixed  object  categories  to  support  reasoning  over  visual  scenes.  While  current  segmentation  models  work  well  when  objects  are  clearly  defined,  they  struggle  with  complex  user  queries  that  refer  to  multiple  or  implicit  objects.  Recent  work  in  reasoning  segmentation,  which  generates  segmentation  masks  from  natural  language  input,  shows  that  vision-language  models  (VLMs)  can  help  address  this.  However,  our  experiments  show  that  existing  models  perform  poorly  on  remote-sensing  images,  which  often  contain  dense  and  varied  content.  To  address  this,  we  introduce  LISAt,  a  vision-language  model  designed  to  describe  remote-sensing  images,  answer  questions  about  them,  and  segment  objects  based  on  user  queries.  LISAt  is  trained  on  GRES,  a  dataset  with  27,615  annotations  across  9,205  images,  and  PreGRES,  a  multimodal  dataset  with  over  one  million  question-answer  pairs.  LISAt  outperforms  geospatial  models  like  RS-GPT4V  by  10.04%  in  BLEU-4  for  image  description  and  improves  on  open-domain  models  in  reasoning  segmentation  by  143.36%  in  generalized  Intersection  over  Union  (gIoU).  These  results  show  how  learning  strong  multimodal  representations  can  improve  scene  understanding,  especially  in  the  geospatial  domain.
■590    ▼aSchool  code:  0028.
■650  4▼aElectrical  engineering
■650  4▼aComputer  science
■650  4▼aInformation  technology
■653    ▼aActive  perception
■653    ▼aLatency  optimization
■653    ▼aMultimodal  representations
■653    ▼aObject  detection  and  segmentation
■653    ▼aReasoning  segmentation
■653    ▼aRepresentation  learning
■690    ▼a0800
■690    ▼a0544
■690    ▼a0984
■690    ▼a0489
■71020▼aUniversity  of  California,  Berkeley▼bElectrical  Engineering  &  Computer  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g87-04B.
■790    ▼a0028
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359144▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Buch Status

    • Reservierung
    • frei buchen
    • Meine Mappe
    • Erste Aufräumarbeiten Anfrage
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Sammlungen
    Registrierungsnummer callnumber Standort Verkehr Status Verkehr Info
    TF17632 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Kredite nur für Ihre Daten gebucht werden. Wenn Sie buchen möchten Reservierungen, klicken Sie auf den Button.

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.