RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation

11/20/2016
by   Guosheng Lin, et al.
0

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments and set new state-of-the-art results on seven public datasets. In particular, we achieve an intersection-over-union score of 83.4 on the challenging PASCAL VOC 2012 dataset, which is the best reported result to date.

READ FULL TEXT

page 1

page 4

page 7

page 8

page 10

research
09/08/2017

An Adaptive Sampling Scheme to Efficiently Train Fully Convolutional Networks for Semantic Segmentation

Deep convolutional neural networks (CNNs) have shown excellent performan...
research
03/10/2016

Exploring Context with Deep Structured models for Semantic Segmentation

State-of-the-art semantic image segmentation methods are mostly based on...
research
04/04/2015

Efficient piecewise training of deep structured models for semantic segmentation

Recent advances in semantic image segmentation have mostly been achieved...
research
07/30/2018

Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network

Semantic labeling for very high resolution (VHR) images in urban areas, ...
research
04/15/2016

High-performance Semantic Segmentation Using Very Deep Fully Convolutional Networks

We propose a method for high-performance semantic image segmentation (or...
research
03/15/2016

Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation

State-of-the-art results of semantic segmentation are established by Ful...
research
04/02/2021

Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy

Kidney stones represent a considerable burden for public health-care sys...

Please sign up or login with your details

Forgot password? Click here to reset