loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: F. X. Erick 1 ; Shrutika S. Sawant 1 ; Stephan Göb 1 ; N. Holzer 1 ; E. W. Lang 2 and Th. Götz 2 ; 3 ; 1

Affiliations: 1 Fraunhofer Institute of integrated Circuits, 91054 Erlangen, Germany ; 2 CIML Group, Biophysics, University of Regensburg, 3040 Regensburg, Germany ; 3 Clinic of Rheumatology, University Hospital Erlangen, 91054 Erlangen, Germany

Keyword(s): Convolutional Neural Network, Deep Learning, Filter Pruning.

Abstract: In this paper, a simple and effective filter pruning method is proposed to simplify the deep convolutional neural network (CNN) and accelerate learning. The proposed method selects the important filters and discards the unimportant ones based on filter dissimilarity analysis. The proposed method searches for filters with decent representative ability and less redundancy, discarding the others. The representative ability and redundancy contained in the filter is evaluated by its correlation with currently selected filters and left over unselected filters. Moreover, the proposed method uses an iterative procedure, so that less representative filters can be discarded evenly from the entire model. The experimental analysis confirmed that a simple filter pruning method can reduce floating point operations (FLOPs) of TernausNet by up to 89.65% on an INRIA Aerial Image Labeling dataset with an only marginal drop in the original accuracy. Furthermore, the proposed method shows promising resu lts in comparison with other state-of-the-art methods. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.236.64.8

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Erick, F.; Sawant, S.; Göb, S.; Holzer, N.; Lang, E. and Götz, T. (2022). A Simple and Effective Convolutional Filter Pruning based on Filter Dissimilarity Analysis. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 139-145. DOI: 10.5220/0010786400003116

@conference{icaart22,
author={F. X. Erick. and Shrutika S. Sawant. and Stephan Göb. and N. Holzer. and E. W. Lang. and Th. Götz.},
title={A Simple and Effective Convolutional Filter Pruning based on Filter Dissimilarity Analysis},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2022},
pages={139-145},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010786400003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - A Simple and Effective Convolutional Filter Pruning based on Filter Dissimilarity Analysis
SN - 978-989-758-547-0
IS - 2184-433X
AU - Erick, F.
AU - Sawant, S.
AU - Göb, S.
AU - Holzer, N.
AU - Lang, E.
AU - Götz, T.
PY - 2022
SP - 139
EP - 145
DO - 10.5220/0010786400003116
PB - SciTePress