BriefGPT.xyz
Jul, 2017
弱监督可支配分割的自适应二值化
Adaptive Binarization for Weakly Supervised Affordance Segmentation
HTML
PDF
Johann Sawatzky, Juergen Gall
TL;DR
本文提出了一种基于稀疏关键点学习卷积神经网络进行可供性分割的迭代方法，并提出了一种自适应的二值化方法，经过两个可供性数据集的实验，我们的方法在弱监督可供性分割领域取得了最好的表现。
Abstract
The concept of
affordance
is important to understand the relevance of object parts for a certain functional interaction.
affordance
types generalize across object categories and are not mutually exclusive. This m
→