New: WildDash 2 with 4256 public frames, new labels & panoptic GT!
See also: RailSem19 dataset for rail scene understanding.
WD1 Instance
NL_ROI_ROB
Non-local ROI
Non-local ROI on Mask R-CNN
imagenet pretrained, coco pretrained, cityscapes, kitti, wilddash, scannet, ade20k
Python
Ubuntu16.04 64bit, i7-8700k @ 3.7GHz, 32 GB RAM, GTX 1080Ti
Non-local RoIs for Instance Segmentation
arXiv preprint
@article{tseng2018non,
title={Non-local RoIs for Instance Segmentation},
author={Tseng, Shou-Yao Roy and Chen, Hwann-Tzong and Tai, Shao-Heng and Liu, Tyng-Luh},
journal={arXiv preprint arXiv:1807.05361},
year={2018}
}