Method Details

Details for method 'PEARL'

name	PEARL
challenge	pixel-level semantic labeling
details	We proposed a novel Parsing with prEdictive feAtuRe Learning (PEARL) model to address the following two problems in video scene parsing: firstly, how to effectively learn meaningful video representations for producing the temporally consistent labeling maps; secondly, how to overcome the problem of insufficient labeled video training data, i.e. how to effectively conduct unsupervised deep learning. To our knowledge, this is the first model to employ predictive feature learning in the video scene parsing.
publication	Video Scene Parsing with Predictive Feature Learning Xiaojie Jin, Xin Li, Huaxin Xiao, Xiaohui Shen, Zhe Lin, Jimei Yang, Yunpeng Chen, Jian Dong, Luoqi Liu, Zequn Jie, Jiashi Feng, and Shuicheng Yan ICCV 2017 https://arxiv.org/abs/1612.00119
project page / code
used Cityscapes data	fine annotations, video
used external data	ImageNet 2012 classification dataset
runtime	n/a
subsampling	no
submission date	May, 2017
previous submissions