# Global Second-order Pooling Convolutional Networks

Source: [Global Second-order Pooling Convolutional Networks](<https://www.sota2.com/research/paper/68fa651f1e209131cea08908>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T05:56:48.640Z

Authors: Zilin Gao, Jiangtao Xie, Qilong Wang, Peihua Li

Published: 2018-11-29T08:15:39.000Z

## Abstract

Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize complex boundaries of thousands of classes in a high-dimensional space, it is critical to learn higher-order representations for enhancing non-linear modeling capability. Recently, Global Second-order Pooling (GSoP), plugged at the end of networks, has attracted increasing attentions, achieving much better performance than classical, first-order networks in a variety of vision tasks. However, how to effectively introduce higher-order representation in earlier layers for improving non-linear capability of ConvNets is still an open problem. In this paper, we propose a novel network model introducing GSoP across from lower to higher layers for exploiting holistic image information throughout a network. Given an input 3D tensor outputted by some previous convolutional layer, we perform GSoP to obtain a covariance matrix which, after nonlinear transformation, is used for tensor scaling along channel dimension. Similarly, we can perform GSoP along spatial dimension for tensor scaling as well. In this way, we can make full use of the second-order statistics of the holistic image throughout a network. The proposed networks are thoroughly evaluated on large-scale ImageNet-1K, and experiments have shown that they outperformed non-trivially the counterparts while achieving state-of-the-art results.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Image Classification on ImageNet 1k (val)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-1k-val.md>): Image Classification; ImageNet-1k (val); Top-1 Accuracy: 77.68.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.12006>)

[PDF](<https://arxiv.org/pdf/1811.12006.pdf>)
