Method Details

Details for method 'Deep Layer Cascade (LC)'

name	Deep Layer Cascade (LC)
challenge	pixel-level semantic labeling
details	We propose a novel deep layer cascade (LC) method to improve the accuracy and speed of semantic segmentation. Unlike the conventional model cascade (MC) that is composed of multiple independent models, LC treats a single deep model as a cascade of several sub-models. Earlier sub-models are trained to handle easy and confident regions, and they progressively feed-forward harder regions to the next sub-model for processing. Convolutions are only calculated on these regions to reduce computations. The proposed method possesses several advantages. First, LC classifies most of the easy regions in the shallow stage and makes deeper stage focuses on a few hard regions. Such an adaptive and 'difficulty-aware' learning improves segmentation performance. Second, LC accelerates both training and testing of deep network thanks to early decisions in the shallow stage. Third, in comparison to MC, LC is an end-to-end trainable framework, allowing joint learning of all sub-models. We evaluate our method on PASCAL VOC and
publication	Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade Xiaoxiao Li, Ziwei Liu, Ping Luo, Chen Change Loy, Xiaoou Tang CVPR 2017 https://arxiv.org/abs/1704.01344
project page / code
used Cityscapes data	fine annotations
used external data	ImageNet
runtime	n/a
subsampling	no
submission date	November, 2016
previous submissions