Not All Pixels Are Equal: Difficulty-Aware Semantic Segmentation via Deep Layer Cascade
Refereed conference paper presented and published in conference proceedings


Full Text

Other information
AbstractWe 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 endto-end trainable framework, allowing joint learning of all sub-models. We evaluate our method on PASCAL VOC and
Cityscapes datasets, achieving state-of-the-art performance and fast speed.
All Author(s) ListXiaoxiao Li, Ping Luo, Chen Change Loy, Xiaoou Tang
Name of ConferenceIEEE Conference on Computer Vision and Pattern Recognition
Start Date of Conference21/07/2017
End Date of Conference26/07/2017
Place of ConferenceHonolulu, Hawaii
Country/Region of ConferenceUnited States of America
Year2017
Month7
LanguagesEnglish-United States

Last updated on 2018-20-01 at 18:58