Training of convolutional networks on multiple heterogeneous datasets for street scene semantic segmentation

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

14 Citations (Scopus)
1 Downloads (Pure)

Abstract

We propose a convolutional network with hierarchical classifiers for per-pixel semantic segmentation, which is able to be trained on multiple, heterogeneous datasets and exploit their semantic hierarchy. Our network is the first to be simultaneously trained on three different datasets from the intelligent vehicles domain, i.e. Cityscapes, GTSDB and Mapillary Vistas, and is able to handle different semantic levelof-detail, class imbalances, and different annotation types, i.e. dense per-pixel and sparse bounding-box labels. We assess our hierarchical approach, by comparing against flat, nonhierarchical classifiers and we show improvements in mean pixel accuracy of 13.0% for Cityscapes classes and 2.4% for Vistas classes and 32.3% for GTSDB classes. Our implementation achieves inference rates of 17 fps at a resolution of 520 x 706 for 108 classes running on a GPU.

Original languageEnglish
Title of host publication2018 IEEE Intelligent Vehicles Symposium, IV 2018
PublisherInstitute of Electrical and Electronics Engineers
Pages1045-1050
Number of pages6
ISBN (Electronic)9781538644522
DOIs
Publication statusPublished - 22 Oct 2018
Event2018 IEEE Intelligent Vehicles Symposium, IV 2018 - Changshu, Suzhou, China
Duration: 26 Sep 201830 Sep 2018

Conference

Conference2018 IEEE Intelligent Vehicles Symposium, IV 2018
CountryChina
CityChangshu, Suzhou
Period26/09/1830/09/18

Fingerprint Dive into the research topics of 'Training of convolutional networks on multiple heterogeneous datasets for street scene semantic segmentation'. Together they form a unique fingerprint.

  • Cite this

    Meletis, P., & Dubbelman, G. (2018). Training of convolutional networks on multiple heterogeneous datasets for street scene semantic segmentation. In 2018 IEEE Intelligent Vehicles Symposium, IV 2018 (pp. 1045-1050). [8500398] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IVS.2018.8500398