SORT: Second-Order Response Transform for Visual Recognition

Yan Wang, Lingxi Xie, Chenxi Liu, Siyuan Qiao, Ya Zhang, Wenjun Zhang, Qi Tian, Alan Yuille

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

49 Scopus citations

Abstract

In this paper, we reveal the importance and benefits of introducing second-order operations into deep neural networks. We propose a novel approach named Second-Order Response Transform (SORT), which appends element-wise product transform to the linear sum of a two-branch network module. A direct advantage of SORT is to facilitate cross-branch response propagation, so that each branch can update its weights based on the current status of the other branch. Moreover, SORT augments the family of transform operations and increases the nonlinearity of the network, making it possible to learn flexible functions to fit the complicated distribution of feature space. SORT can be applied to a wide range of network architectures, including a branched variant of a chain-styled network and a residual network, with very light-weighted modifications. We observe consistent accuracy gain on both small (CIFAR10, CIFAR100 and SVHN) and big (ILSVRC2012) datasets. In addition, SORT is very efficient, as the extra computation overhead is less than 5%.

Original languageEnglish
Title of host publicationProceedings - 2017 IEEE International Conference on Computer Vision, ICCV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1368-1377
Number of pages10
ISBN (Electronic)9781538610329
DOIs
StatePublished - 22 Dec 2017
Externally publishedYes
Event16th IEEE International Conference on Computer Vision, ICCV 2017 - Venice, Italy
Duration: 22 Oct 201729 Oct 2017

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2017-October
ISSN (Print)1550-5499

Conference

Conference16th IEEE International Conference on Computer Vision, ICCV 2017
Country/TerritoryItaly
CityVenice
Period22/10/1729/10/17

Fingerprint

Dive into the research topics of 'SORT: Second-Order Response Transform for Visual Recognition'. Together they form a unique fingerprint.

Cite this