King's College London

Research portal

Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels

Research output: Chapter in Book/Report/Conference proceedingConference paper

Standard

Stochastic filter groups for multi-task cnns : Learning specialist and generalist convolution kernels. / Bragman, Felix; Tanno, Ryutaro; Ourselin, Sebastien; Alexander, Daniel; Cardoso, Jorge.

Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1385-1394 9009037 (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceedingConference paper

Harvard

Bragman, F, Tanno, R, Ourselin, S, Alexander, D & Cardoso, J 2019, Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels. in Proceedings - 2019 International Conference on Computer Vision, ICCV 2019., 9009037, Proceedings of the IEEE International Conference on Computer Vision, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., pp. 1385-1394, 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea, Republic of, 27/10/2019. https://doi.org/10.1109/ICCV.2019.00147

APA

Bragman, F., Tanno, R., Ourselin, S., Alexander, D., & Cardoso, J. (2019). Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels. In Proceedings - 2019 International Conference on Computer Vision, ICCV 2019 (pp. 1385-1394). [9009037] (Proceedings of the IEEE International Conference on Computer Vision; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV.2019.00147

Vancouver

Bragman F, Tanno R, Ourselin S, Alexander D, Cardoso J. Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels. In Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1385-1394. 9009037. (Proceedings of the IEEE International Conference on Computer Vision). https://doi.org/10.1109/ICCV.2019.00147

Author

Bragman, Felix ; Tanno, Ryutaro ; Ourselin, Sebastien ; Alexander, Daniel ; Cardoso, Jorge. / Stochastic filter groups for multi-task cnns : Learning specialist and generalist convolution kernels. Proceedings - 2019 International Conference on Computer Vision, ICCV 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1385-1394 (Proceedings of the IEEE International Conference on Computer Vision).

Bibtex Download

@inbook{654c04b59e154cadb76211789f95df37,
title = "Stochastic filter groups for multi-task cnns: Learning specialist and generalist convolution kernels",
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' and 'generalist' groups, which are specific to and 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 the proposed method generalises across multiple tasks and shows improved performance over baseline methods.",
author = "Felix Bragman and Ryutaro Tanno and Sebastien Ourselin and Daniel Alexander and Jorge Cardoso",
year = "2019",
month = "10",
doi = "10.1109/ICCV.2019.00147",
language = "English",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1385--1394",
booktitle = "Proceedings - 2019 International Conference on Computer Vision, ICCV 2019",
address = "United States",

}

RIS (suitable for import to EndNote) Download

TY - CHAP

T1 - Stochastic filter groups for multi-task cnns

T2 - Learning specialist and generalist convolution kernels

AU - Bragman, Felix

AU - Tanno, Ryutaro

AU - Ourselin, Sebastien

AU - Alexander, Daniel

AU - Cardoso, Jorge

PY - 2019/10

Y1 - 2019/10

N2 - 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' and 'generalist' groups, which are specific to and 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 the proposed method generalises across multiple tasks and shows improved performance over baseline methods.

AB - 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' and 'generalist' groups, which are specific to and 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 the proposed method generalises across multiple tasks and shows improved performance over baseline methods.

UR - http://www.scopus.com/inward/record.url?scp=85081913659&partnerID=8YFLogxK

U2 - 10.1109/ICCV.2019.00147

DO - 10.1109/ICCV.2019.00147

M3 - Conference paper

AN - SCOPUS:85081913659

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 1385

EP - 1394

BT - Proceedings - 2019 International Conference on Computer Vision, ICCV 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454