Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
Yan Wang, Lingxi Xie, Siyuan Qiao, Ya Zhang, Wenjun Zhang, Alan L. Yuille
Abstract
Convolution is spatially-symmetric, i.e., the visual features are independent of its position in the image, which limits its ability to use spatial information. This paper addresses this issue by a recalibration process, which refers to the surrounding region of each neuron, computes an importance value and multiplies it to the original neural response. Our approach is named multi-scale spatially-asymmetric recalibration (MS-SAR), which, besides introducing spatial asymmetry into convolution, extracts visual cues from regions at multiple scales to allow richer information to be incorporated. MS-SAR is implemented in an efficient way, so that only small fractions of extra parameters and computations are required. We apply MS-SAR to several popular network architectures, in which all convolutional layers are recalibrated, and demonstrate superior performance in both CIFAR and ILSVRC2012 classification tasks.
BibTeX
@inproceedings{eccv2018_multiscalespatia,
title = {Multi-Scale Spatially-Asymmetric Recalibration for Image Classification},
author = {Yan Wang and Lingxi Xie and Siyuan Qiao and Ya Zhang and Wenjun Zhang and Alan L. Yuille},
booktitle = {ECCV 2018},
year = {2018}
}