HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

BlitzNet: A Real-Time Deep Network for Scene Understanding

Nikita Dvornik 1 Konstantin Shmelkov 1 Julien Mairal 1 Cordelia Schmid 1
1 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [27 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01573361
Contributor : Nikita Dvornik Connect in order to contact the contributor
Submitted on : Wednesday, August 9, 2017 - 11:43:46 AM
Last modification on : Friday, February 4, 2022 - 3:21:12 AM

File

egpaper_final.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

723

Files downloads

10594