Understanding Convolution for Semantic Segmentation
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-theart overall on the KITTI road estimation benchmark and the PASCAL VOC2012 segmentation task.
by Panqu Wang, Pengfei Chen, Ye Yuan, Ding Liu, Zehua Huang, Xiaodi Hou, and Garrison Cottrell.
Build MXNet (only tested on the TuSimple version)
git clone --recursive email@example.com:TuSimple/mxnet.git vim make/config.mk (we should have USE_CUDA = 1, modify USE_CUDA_PATH, and have USE_CUDNN = 1 to enable GPU usage.) make -j cd python python setup.py develop --user