Split-Merge Pooling

TL;DR

Split-Merge pooling is a novel method that preserves spatial information while providing a large receptive field, improving dense semantic segmentation accuracy on large images without subsampling.

Contribution

The paper introduces Split-Merge pooling, a new pooling technique that maintains spatial resolution and enhances receptive field size in deep networks for dense prediction tasks.

Findings

Improved semantic segmentation accuracy on Cityscapes and GTA-5 datasets.

Replaced max-pooling and striding convolutions with Split-Merge pooling in ResNet.

Achieved significant accuracy gains without losing spatial information.

Abstract

There are a variety of approaches to obtain a vast receptive field with convolutional neural networks (CNNs), such as pooling or striding convolutions. Most of these approaches were initially designed for image classification and later adapted to dense prediction tasks, such as semantic segmentation. However, the major drawback of this adaptation is the loss of spatial information. Even the popular dilated convolution approach, which in theory is able to operate with full spatial resolution, needs to subsample features for large image sizes in order to make the training and inference tractable. In this work, we introduce Split-Merge pooling to fully preserve the spatial information without any subsampling. By applying Split-Merge pooling to deep networks, we achieve, at the same time, a very large receptive field. We evaluate our approach for dense semantic segmentation of large image sizes taken from the Cityscapes and GTA-5 datasets. We demonstrate that by replacing max-pooling and striding convolutions with our split-merge pooling, we are able to improve the accuracy of different variations of ResNet significantly.