Gaussian Filter in CRF Based Semantic Segmentation
arXiv:1709.00516
Abstract
Artificial intelligence is making great changes in academy and industry with the fast development of deep learning, which is a branch of machine learning and statistical learning. Fully convolutional network [1] is the standard model for semantic segmentation. Conditional random fields coded as CNN [2] or RNN [3] and connected with FCN has been successfully applied in object detection [4]. In this paper, we introduce a multi-resolution neural network for FCN and apply Gaussian filter to the extended CRF kernel neighborhood and the label image to reduce the oscillating effect of CRF neural network segmentation, thus achieve higher precision and faster training speed.
11 pages, 9 figures, 2 tables
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- Conditional Random Fields as Recurrent Neural Networks
- Fully Convolutional Networks for Semantic Segmentation
- YOLO9000: Better, Faster, Stronger
- U-Net: Convolutional Networks for Biomedical Image Segmentation