Method Details

Details for method 'APMoE_seg_ROB'

name	APMoE_seg_ROB
challenge	pixel-level semantic labeling
details	The Pixel-level Attentional Gating (PAG) unit is trained to choose for each pixel the pooling size to adopt to aggregate contextual region around it. There are multiple branches with different dilate rates for varied pooling size, thus varying receptive field. For this ROB challenge, PAG is expected to robustly aggregate information for final prediction. This is our entry for Robust Vision Challenge 2018 workshop (ROB). The model is based on ResNet50, trained over mixed dataset of Cityscapes, ScanNet and Kitti.
publication	Pixel-wise Attentional Gating for Parsimonious Pixel Labeling Shu Kong, Charless Fowlkes arxiv https://arxiv.org/abs/1805.01556
project page / code	https://github.com/aimerykong/Pixel-Attentional-Gating
used Cityscapes data	fine annotations
used external data	ImageNet, mixted training set of Cityscapes, Kitti, ScanNet
runtime	0.9 s Geforce Titan X
subsampling	no
submission date	May, 2018
previous submissions