Image semantic segmentation based on convolutional neural network and conditional random field

Abstract

Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation through the use of contextual information; First, we propose to exploit a pre-trained AlexNet to generate deep features, and then we exploit the CRF to achieve image semantic segmentation. Experiments on Weizmann horse and Stanford Background benchmarks demonstrate the promise of the proposed method.