Split-Merge Pooling

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.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Residual Learning for Image Recognition
• Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
• Multi-Scale Context Aggregation by Dilated Convolutions
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• Pyramid Scene Parsing Network
• Dilated Residual Networks
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
• Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation