Robust Semantic Segmentation with Ladder-DenseNet Models

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 convolutional architecture featuring a modified DenseNet-169 model in the downsampling datapath, and only one convolu...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Krešo, Ivan, Marin Oršić, Bevandić, Petra, Šegvić, Siniša
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 09.06.2018
Subjects
Benchmarks
Convolution
Model testing
Semantic segmentation
Semantics
Online AccessGet full text

Cover

More Information
Summary: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 convolutional architecture featuring a modified DenseNet-169 model in the downsampling datapath, and only one convolution in each stage of the upsampling datapath. Due to limited computing resources, we perform the training only on Cityscapes Fine train+val, ScanNet train, WildDash val and KITTI train. We evaluate the trained model on the test subsets of the four benchmarks in concordance with the guidelines of the Robust Vision Challenge ROB 2018. The performed experiments reveal several interesting findings which we describe and discuss.
ISSN:2331-8422