BlitzNet: A Real-Time Deep Network for Scene Understanding

Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4154-4162

Abstract

Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly performs object detection and semantic segmentation in one forward pass, allowing real-time computations. Besides the computational gain of having a single network to perform several tasks, we show that object detection and semantic segmentation benefit from each other in terms of accuracy. Experimental results for VOC and COCO datasets show state-of-the-art performance for object detection and segmentation among real time systems.

Related Material

[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Dvornik_2017_ICCV,
author = {Dvornik, Nikita and Shmelkov, Konstantin and Mairal, Julien and Schmid, Cordelia},
title = {BlitzNet: A Real-Time Deep Network for Scene Understanding},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}