UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at http://www.ucl.ac.uk/finance/research/post_award/post_award_contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Learning task-specific and shared representations in medical imaging
  • Publication Type:
    Conference
  • Authors:
    Bragman FJS, Tanno R, Ourselin S, Alexander DC, Cardoso MJ
  • Publisher:
    Springer
  • Publication date:
    10/10/2019
  • Pagination:
    374, 383
  • Published proceedings:
    MICCAI 2019 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part IV
  • Volume:
    11767 LNCS
  • ISBN-13:
    9783030322502
  • Status:
    Published
  • Name of conference:
    Medical Image Computing and Computer Assisted Intervention – MICCAI 2019 - 22nd International Conference
  • Conference place:
    Shenzhen, China
  • Conference start date:
    13/10/2019
  • Conference finish date:
    17/10/2019
  • Print ISSN:
    0302-9743
Abstract
© Springer Nature Switzerland AG 2019. The performance of multi-task learning hinges on the design of feature sharing between tasks; a process which is combinatorial in the network depth and task count. Hand-crafting an architecture based on human intuitions of task relationships is therefore suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in Convolutional Neural Networks (CNNs) for multi-task learning of semantic tasks. We introduce Stochastic Filter Groups; which is a mechanism that groups convolutional kernels into task-specific and shared groups to learn an optimal kernel allocation. They facilitate learning optimal shared and task specific representations. We employ variational inference to learn the posterior distribution over the possible grouping of kernels and CNN weights. Experiments on MRI-based prostate radiotherapy organ segmentation and CT synthesis demonstrate that the proposed method learns optimal task allocations that are inline with human-optimised networks whilst improving performance over competing baselines.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers
Author
Dept of Computer Science
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by