BriefGPT.xyz
Nov, 2017
深度极端割：从极值点到目标分割
Deep Extreme Cut: From Extreme Points to Object Segmentation
HTML
PDF
Kevis-Kokitsi Maninis, Sergi Caelles, Jordi Pont-Tuset, Luc Van Gool
TL;DR
本文旨在探讨将物体的极点作为输入, 结合卷积神经网络(CNN)中的高斯分布, 实现图片和视频物体分割, 并且在各种基准测试和数据集中证明了该方法的高精度和易用性。
Abstract
This paper explores the use of
extreme points
in an object (left-most, right-most, top, bottom pixels) as input to obtain precise
object segmentation
for images and videos. We do so by adding an extra channel to
→