# Improving the Resolution of CNN Feature Maps Efficiently with Multisampling

Source: [Improving the Resolution of CNN Feature Maps Efficiently with Multisampling](<https://www.sota2.com/research/paper/68fa70bc1e209131cea4cf1d>)

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

Data updated: 2025-10-26T01:48:53.779Z

Authors: Shayan Sadigh, Pradeep Sen

Published: 2018-05-28T04:29:02.000Z

## Abstract

We describe a new class of subsampling techniques for CNNs, termed multisampling, that significantly increases the amount of information kept by feature maps through subsampling layers. One version of our method, which we call checkered subsampling, significantly improves the accuracy of state-of-the-art architectures such as DenseNet and ResNet without any additional parameters and, remarkably, improves the accuracy of certain pretrained ImageNet models without any training or fine-tuning. We glean possible insight into the nature of data augmentations and demonstrate experimentally that coarse feature maps are bottlenecking the performance of neural networks in image classification.

## 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/1805.10766>)

[PDF](<https://arxiv.org/pdf/1805.10766.pdf>)