BriefGPT.xyz
Nov, 2018
非线性输出转换的深度结构化预测
Deep Structured Prediction with Nonlinear Output Transformations
HTML
PDF
Colin Graber, Ofer Meshi, Alexander Schwing
TL;DR
本研究提出一种新型模型，可用于语义分割等任务中，综合多种现有方法，实现了图像分割中非线性输出空间转换，同时保持了现有推理技术的适用性。
Abstract
deep structured models
are widely used for tasks like
semantic segmentation
, where explicit correlations between variables provide important prior information which generally helps to reduce the data needs of dee
→