Pedestrian detection aided by deep learning semantic tasks
Refereed conference paper presented and published in conference proceedings

Times Cited
Altmetrics Information

Other information
AbstractDeep learning methods have achieved great successes in pedestrian detection, owing to its ability to learn discriminative features from raw pixels. However, they treat pedestrian detection as a single binary classification task, which may confuse positive with hard negative samples (Fig.1 (a)). To address this ambiguity, this work jointly optimize pedestrian detection with semantic tasks, including pedestrian attributes (e.g. 'carrying backpack') and scene attributes (e.g. 'vehicle', '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 deep model is carefully designed to coordinate tasks and reduce discrepancies among datasets. Extensive evaluations show that the proposed approach outperforms the state-of-the-art on the challenging Caltech [9] and ETH [10] datasets where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively.
All Author(s) ListTian Y., Luo P., Wang X., Tang X.
Name of ConferenceIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
Start Date of Conference07/06/2015
End Date of Conference12/06/2015
Place of ConferenceBoston
Country/Region of ConferenceUnited States of America
Detailed descriptionorganized by IEEE computer society,
Volume Number07-12-June-2015
Pages5079 - 5087
LanguagesEnglish-United Kingdom

Last updated on 2021-26-11 at 23:53