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
Stochastic Filter Groups for Multi-Task CNNs: Learning Specialist and Generalist Convolution Kernels
  • Publication Type:
    Conference
  • Authors:
    Bragman FJS, Tanno R, Ourselin S, Alexander DC, Cardoso MJ
  • Publisher:
    IEEE
  • Publication date:
    27/02/2020
  • Published proceedings:
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Name of conference:
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • Conference place:
    Seoul, Korea (South)
  • Conference start date:
    27/10/2019
  • Conference finish date:
    02/11/2019
  • Keywords:
    cs.CV, cs.CV, cs.LG
  • Notes:
    Accepted for oral presentation at ICCV 2019
Abstract
The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design of feature sharing between tasks within the architecture. The number of possible sharing patterns are combinatorial in the depth of the network and the number of tasks, and thus hand-crafting an architecture, purely based on the human intuitions of task relationships can be time-consuming and suboptimal. In this paper, we present a probabilistic approach to learning task-specific and shared representations in CNNs for multi-task learning. Specifically, we propose "stochastic filter groups'' (SFG), a mechanism to assign convolution kernels in each layer to "specialist'' or "generalist'' groups, which are specific to or shared across different tasks, respectively. The SFG modules determine the connectivity between layers and the structures of task-specific and shared representations in the network. We employ variational inference to learn the posterior distribution over the possible grouping of kernels and network parameters. Experiments demonstrate that the proposed method generalises across multiple tasks and shows improved performance over baseline methods.
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