SORT: Second-Order Response Transform for Visual Recognition

Yan Wang, Lingxi Xie, Chenxi Liu, Siyuan Qiao, Ya Zhang, Wenjun Zhang, Qi Tian, Alan Yuille; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 1359-1368


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%.

Related Material

[pdf] [arXiv]
author = {Wang, Yan and Xie, Lingxi and Liu, Chenxi and Qiao, Siyuan and Zhang, Ya and Zhang, Wenjun and Tian, Qi and Yuille, Alan},
title = {SORT: Second-Order Response Transform for Visual Recognition},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}