RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks.

Loading...
Thumbnail Image

Date

2018

Journal Title

Journal ISSN

Volume Title

Repository Usage Stats

109
views
44
downloads

Abstract

Explicit encoding of group actions in deep features makes it possible for convolutional neural networks (CNNs) to handle global deformations of images, which is critical to success in many vision tasks. This paper proposes to decompose the convolutional filters over joint steerable bases across the space and the group geometry simultaneously, namely a rotation-equivariant CNN with decomposed convolutional filters (RotDCF). This decomposition facilitates computing the joint convolution, which is proved to be necessary for the group equivariance. It significantly reduces the model size and computational complexity while preserving performance, and truncation of the bases expansion serves implicitly to regularize the filters. On datasets involving in-plane and out-of-plane object rotations, RotDCF deep features demonstrate greater robustness and interpretability than regular CNNs. The stability of the equivariant representation to input variations is also proved theoretically under generic assumptions on the filters in the decomposed form. The RotDCF framework can be extended to groups other than rotations, providing a general approach which achieves both group equivariance and representation stability at a reduced model size.

Department

Description

Provenance

Citation

Scholars@Duke

Sapiro

Guillermo Sapiro

James B. Duke Distinguished Professor of Electrical and Computer Engineering

Guillermo Sapiro received his B.Sc. (summa cum laude), M.Sc., and Ph.D. from the Department of Electrical Engineering at the Technion, Israel Institute of Technology, in 1989, 1991, and 1993 respectively. After post-doctoral research at MIT, Dr. Sapiro became Member of Technical Staff at the research facilities of HP Labs in Palo Alto, California. He was with the Department of Electrical and Computer Engineering at the University of Minnesota, where he held the position of Distinguished McKnight University Professor and Vincentine Hermes-Luh Chair in Electrical and Computer Engineering. Currently he is the Edmund T. Pratt, Jr. School Professor with Duke University.

G. Sapiro works on theory and applications in computer vision, computer graphics, medical imaging, image analysis, and machine learning. He has authored and co-authored over 300 papers in these areas and has written a book published by Cambridge University Press, January 2001.

G. Sapiro was awarded the Gutwirth Scholarship for Special Excellence in Graduate Studies in 1991,  the Ollendorff Fellowship for Excellence in Vision and Image Understanding Work in 1992,  the Rothschild Fellowship for Post-Doctoral Studies in 1993, the Office of Naval Research Young Investigator Award in 1998,  the Presidential Early Career Awards for Scientist and Engineers (PECASE) in 1998, the National Science Foundation Career Award in 1999, and the National Security Science and Engineering Faculty Fellowship in 2010. He received the test of time award at ICCV 2011. He was elected to the American Academy of Arts and Sciences on 2018.

G. Sapiro is a Fellow of IEEE and SIAM.

G. Sapiro was the founding Editor-in-Chief of the SIAM Journal on Imaging Sciences.


Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.