BriefGPT.xyz
Nov, 2015
学习密集卷积嵌入用于语义分割
Segmentation-Aware Convolutional Nets
HTML
PDF
Adam W. Harley, Konstantinos G. Derpanis, Iasonas Kokkinos
TL;DR
本文提出了基于像素 embeddings 的深层卷积神经网络,利用嵌入学习像素之间的距离来推断像素是否属于同一区域,并证明其与 DCNN 结合使用可以显著提高每个像素分类的准确性。
Abstract
This paper proposes a new
deep convolutional neural network
(DCNN) architecture for learning
semantic segmentation
. The main idea is to train the DCNN to produce internal representations that respect object bound
→