Can I read Pedestrian Detection aided by Deep Learning Semantic Tasks on EtoBox?

Pedestrian Detection aided by Deep Learning Semantic Tasks by Tian, Yonglong; Luo, Ping; Wang, Xiaogang; Tang, Xiaoou is a scholarly article available to read on EtoBox.

What is Pedestrian Detection aided by Deep Learning Semantic Tasks about?

Deep learning methods have achieved great success in pedestrian detection, owing to its ability to learn features from raw pixels. However, they mainly capture middle-level representations, such as pose of pedestrian, but confuse positive with hard negative samples, which have large ambiguity, e.g. the shape and appearance of `tree trunk' or `wire pole' are similar to pedestrian in certain viewpoint. This ambiguity can be distinguished by high-level representation. To this end, this work jointly optimizes pedestrian detection with semantic tasks, including pedestrian attributes (e.g. `carrying backpack') and scene attributes (e.g. `road', `tree', and `horizontal'). Rather than expensively annotating scene attributes, we transfer attributes information from existing scene segmentation datasets to the pedestrian dataset, by proposing a novel deep model to learn high-level features from multiple tasks and multiple data sources. Since distinct tasks have distinct convergence rates and data from different datasets have different distributions, a multi-task objective function is carefully designed to coordinate tasks and reduce discrepancies among datasets. The importance coefficients of

Author

Tian, Yonglong; Luo, Ping; Wang, Xiaogang; Tang, Xiaoou

Published

2014

Language

EN