# Gaussian Filter in CRF Based Semantic Segmentation

Source: [Gaussian Filter in CRF Based Semantic Segmentation](<https://www.sota2.com/research/paper/68fa639c1e209131ce9ff9c2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:44:17.219Z

Authors: Yichi Gu, Qisheng Wu, Jing Li, Kai Cheng

Published: 2017-09-02T01:38:34.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1709.00516>)

[PDF](<https://arxiv.org/pdf/1709.00516.pdf>)