BriefGPT.xyz
Jun, 2018
基于Ladder-DenseNet模型的鲁棒语义分割
Robust Semantic Segmentation with Ladder-DenseNet Models
HTML
PDF
Ivan Krešo, Marin Oršić, Petra Bevandić, Siniša Šegvić
TL;DR
本研究对语义分割进行了实验，利用具备ladder-style卷积架构的修改版DenseNet-169模型，针对四个基准数据集进行了预测，并在ROB 2018的指导下进行了验证。实验结果表明了几个有趣的发现。
Abstract
We present
semantic segmentation
experiments with a model capable to perform predictions on four
benchmark datasets
: Cityscapes, ScanNet, WildDash and KITTI. We employ a ladder-style
→