# Analyzing the Dependency of ConvNets on Spatial Information

Source: [Analyzing the Dependency of ConvNets on Spatial Information](<https://www.sota2.com/research/paper/68fa66fd1e209131cea1385c>)

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

Data updated: 2025-10-25T22:03:19.943Z

Authors: Yue Fan, Yongqin Xian, Max Maria Losch, Bernt Schiele

Published: 2020-02-05T15:22:32.000Z

## Abstract

Intuitively, image classification should profit from using spatial information. Recent work, however, suggests that this might be overrated in standard CNNs. In this paper, we are pushing the envelope and aim to further investigate the reliance on spatial information. We propose spatial shuffling and GAP+FC to destroy spatial information during both training and testing phases. Interestingly, we observe that spatial information can be deleted from later layers with small performance drops, which indicates spatial information at later layers is not necessary for good performance. For example, test accuracy of VGG-16 only drops by 0.03% and 2.66% with spatial information completely removed from the last 30% and 53% layers on CIFAR100, respectively. Evaluation on several object recognition datasets (CIFAR100, Small-ImageNet, ImageNet) with a wide range of CNN architectures (VGG16, ResNet50, ResNet152) shows an overall consistent pattern.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.01827>)

[PDF](<https://arxiv.org/pdf/2002.01827.pdf>)