Method Details

Details for method 'L2-SP'

name	L2-SP
challenge	pixel-level semantic labeling
details	With a simple variant of weight decay, L2-SP regularization (see the paper for details), we reproduced PSPNet based on original ResNet-101 using "train_fine + train_extra" set (2975 + 20000 images), with a small batch size 8. The sync batch normalization layer is implemented in Tensorflow (see the code).
publication	Explicit Inductive Bias for Transfer Learning with Convolutional Networks Xuhong Li, Yves Grandvalet, Franck Davoine arxiv https://arxiv.org/abs/1802.01483
project page / code	https://github.com/holyseven/PSPNet-TF-Reproduce
used Cityscapes data	fine annotations, coarse annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	March, 2018
previous submissions