CVSep 2, 2017

Gaussian Filter in CRF Based Semantic Segmentation

arXiv:1709.00516v1
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for semantic segmentation in computer vision.

The paper tackles the oscillating effect in CRF-based semantic segmentation by applying Gaussian filters to the CRF kernel neighborhood and label image, achieving higher precision and faster training speed.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes