loading
Papers

Research.Publish.Connect.

Paper

Authors: Benjamin Coors 1 ; Alexandru Condurache 2 ; Alfred Mertins 3 and Andreas Geiger 4

Affiliations: 1 MPI for Intelligent Systems and Robert Bosch GmbH, Germany ; 2 Robert Bosch GmbH, Germany ; 3 University of Lübeck, Germany ; 4 MPI for Intelligent Systems and ETH Zürich, Germany

ISBN: 978-989-758-290-5

Keyword(s): Deep Learning, Transformation Invariance, Weak Supervision, Object Recognition.

Abstract: Deep convolutional neural networks are the current state-of-the-art solution to many computer vision tasks. However, their ability to handle large global and local image transformations is limited. Consequently, extensive data augmentation is often utilized to incorporate prior knowledge about desired invariances to geometric transformations such as rotations or scale changes. In this work, we combine data augmentation with an unsupervised loss which enforces similarity between the predictions of augmented copies of an input sample. Our loss acts as an effective regularizer which facilitates the learning of transformation invariant representations. We investigate the effectiveness of the proposed similarity loss on rotated MNIST and the German Traffic Sign Recognition Benchmark (GTSRB) in the context of different classification models including ladder networks. Our experiments demonstrate improvements with respect to the standard data augmentation approach for supervised and semi-supe rvised learning tasks, in particular in the presence of little annotated data. In addition, we analyze the performance of the proposed approach with respect to its hyperparameters, including the strength of the regularization as well as the layer where representation similarity is enforced. (More)

PDF ImageFull Text

Download
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 100.25.43.188

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:
Coors, B.; Condurache, A.; Mertins, A. and Geiger, A. (2018). Learning Transformation Invariant Representations with Weak Supervision.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP, ISBN 978-989-758-290-5, pages 64-72. DOI: 10.5220/0006549000640072

@conference{visapp18,
author={Benjamin Coors. and Alexandru Condurache. and Alfred Mertins. and Andreas Geiger.},
title={Learning Transformation Invariant Representations with Weak Supervision},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,},
year={2018},
pages={64-72},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006549000640072},
isbn={978-989-758-290-5},
}

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5 VISAPP: VISAPP,
TI - Learning Transformation Invariant Representations with Weak Supervision
SN - 978-989-758-290-5
AU - Coors, B.
AU - Condurache, A.
AU - Mertins, A.
AU - Geiger, A.
PY - 2018
SP - 64
EP - 72
DO - 10.5220/0006549000640072

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.