×
This website is optimized for a screen size of 1025x800px or higher. If you are accessing this website with a lower resolution, some features are not fully functional.

ROB 2018 Instance Segmentation Finalists

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

This is the WildDash ranking of all ROB submissions for the 2018 Robust Vision Challenge. The challenge uses a Schulze-method-based multiranking approach to aggregate the individual rankings of WildDash into one global ranking for the challenge. Thus, the ranking on this page differs from the ranking used on the WildDash main leaderboard.
The final overall ranking (aggregated for Cityscapes, KITTI, ScanNet and Wilddash) can be seen here. The ROB challenge continues as a permanent meta-benchmark (see the official homepage for more details)!
go back to leaderboard
NL_ROI_ROB
MaskRCNN_ROB
MRCNN_VSCMLab_ROB
BAMRCNN_ROB