Method Details

Details for method 'Deep Layer Cascade (LC)'


Method overview

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
project page / code
used Cityscapes data fine annotations
used external data ImageNet
runtime n/a
subsampling no
submission date November, 2016
previous submissions


Average results

Metric Value
IoU Classes 71.0873
iIoU Classes 47.0059
IoU Categories 88.1093
iIoU Categories 74.1373


Class results

Class IoU iIoU
road 98.0943 -
sidewalk 82.7777 -
building 91.1705 -
wall 47.0663 -
fence 52.8011 -
pole 57.3194 -
traffic light 63.8946 -
traffic sign 70.6799 -
vegetation 92.4828 -
terrain 70.5149 -
sky 94.1945 -
person 81.2132 60.4551
rider 57.9176 36.0679
car 94.0807 87.9179
truck 50.1397 26.0923
bus 59.5682 42.1022
train 57.034 32.2838
motorcycle 58.6405 35.1202
bicycle 71.0684 56.0078


Category results

Category IoU iIoU
flat 98.4356 -
nature 92.1254 -
object 64.5369 -
sky 94.1945 -
construction 91.5332 -
human 82.4686 62.0367
vehicle 93.4706 86.2379



Download results as .csv file

Benchmark page