BlitzNet: A Real-Time Deep Network for Scene Understanding - Archive ouverte HAL
Conference Papers Year : 2017

BlitzNet: A Real-Time Deep Network for Scene Understanding

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.
Fichier principal
Vignette du fichier
egpaper_final.pdf (2.61 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01573361 , version 1 (09-08-2017)

Identifiers

Cite

Nikita Dvornik, Konstantin Shmelkov, Julien Mairal, Cordelia Schmid. BlitzNet: A Real-Time Deep Network for Scene Understanding. ICCV 2017 - International Conference on Computer Vision, Oct 2017, Venise, Italy. pp.4174-4182, ⟨10.1109/ICCV.2017.447⟩. ⟨hal-01573361⟩
826 View
10728 Download

Altmetric

Share

More