IEEE - Institute of Electrical and Electronics Engineers, Inc. - TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Author(s): Dmitry Laptev ; Nikolay Savinov ; Joachim M. Buhmann ; Marc Pollefeys
Publisher: IEEE - Institute of Electrical and Electronics Engineers, Inc.
Publication Date: 1 June 2016
Conference Location: Las Vegas, NV, USA
Conference Date: 27 June 2016
Page(s): 289 - 297
ISBN (Electronic): 978-1-4673-8851-1
ISSN (Electronic): 1063-6919
DOI: 10.1109/CVPR.2016.38
Regular:

In this paper we present a deep neural network topology that incorporates a simple to implement transformationinvariant pooling operator (TI-POOLING). This operator is able to efficiently... View More

Advertisement