×

Algorithm Details

New: WildDash 2 with 4256 public frames, new labels & panoptic GT!  
See also: RailSem19 dataset for rail scene understanding.

Challenge

WD2 Instance

Acronym

seamseg_rvcsubset

Method title

seamseg_rvcsubset

Method description

Seamless Scene Segmentation Resnet101, pretrained on Imagenet; supplied with altered MVD to include WildDash2 classes; does not contain other RVC label policies (i.e. no COCO-specific classes ; rvcsubset and not a proper submission)
Trained by Oliver Zendel as a baseline for RVC

Training data

Mapillary Vistas dataset with added van/pickup truck relabeling

Additional data

Source code

Publication

Title

Seamless Scene Segmentation

Authors

Porzi, Lorenzo and Rota Bulò, Samuel and Colovic, Aleksander and Kontschieder, Peter

Conference

CVPR 2019

BibTex

@InProceedings{Porzi_2019_CVPR,
author = {Porzi, Lorenzo and Rota Bul\`o, Samuel and Colovic, Aleksander and Kontschieder, Peter},
title = {Seamless Scene Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}