Understanding Convolution for Semantic Segmentation

TL;DR

This paper introduces novel convolutional techniques, DUC and HDC, to enhance pixel-level semantic segmentation, achieving state-of-the-art results on multiple benchmarks by capturing detailed information and enlarging receptive fields.

Contribution

The paper proposes dense upsampling convolution (DUC) and hybrid dilated convolution (HDC) frameworks to improve segmentation accuracy and address issues in existing convolutional methods.

Findings

Achieved 80.1% mIOU on Cityscapes dataset.

State-of-the-art results on KITTI road estimation.

Best performance on PASCAL VOC2012 segmentation.

Abstract

Recent advances in deep learning, especially deep convolutional neural networks (CNNs), have led to significant improvement over previous semantic segmentation systems. Here we show how to improve pixel-wise semantic segmentation by manipulating convolution-related operations that are of both theoretical and practical value. First, we design dense upsampling convolution (DUC) to generate pixel-level prediction, which is able to capture and decode more detailed information that is generally missing in bilinear upsampling. Second, we propose a hybrid dilated convolution (HDC) framework in the encoding phase. This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation. We evaluate our approaches thoroughly on the Cityscapes dataset, and achieve a state-of-art result of 80.1% mIOU in the test set at the time of submission. We also have achieved state-of-the-art overall on the KITTI road estimation benchmark and the PASCAL VOC2012 segmentation task. Our source code can be found at https://github.com/TuSimple/TuSimple-DUC .