Header

UZH-Logo

Maintenance Infos

LiteEdge: Lightweight Semantic Edge Detection Network


Wang, Hao; Mohamed, Hasan; Wang, Zuowen; Rueckauer, Bodo; Liu, Shih-Chii (2021). LiteEdge: Lightweight Semantic Edge Detection Network. In: 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, 11 October 2021 - 17 October 2021, IEEE.

Abstract

Scene parsing is a critical component for understanding complex scenes in applications such as autonomous driving. Semantic segmentation networks are typically reported for scene parsing but semantic edge networks have also become of interest because of the sparseness of the segmented maps. This work presents an end-to-end trained lightweight deep semantic edge detection architecture called LiteEdge suitable for edge deployment. By utilizing hierarchical supervision and a new weighted multi-label loss function to balance different edge classes during training, LiteEdge predicts with high accuracy category-wise binary edges. Our LiteEdge network with only ≈ 3M parameters, has a semantic edge prediction accuracy of 52.9% mean maximum F (MF) score on the Cityscapes dataset. This accuracy was evaluated on the network trained to produce a low resolution edge map. The network can be quantized to 6-bit weights and 8-bit activations and shows only a 2% drop in the mean MF score. This quantization leads to a memory footprint savings of 6X for an edge device.

Abstract

Scene parsing is a critical component for understanding complex scenes in applications such as autonomous driving. Semantic segmentation networks are typically reported for scene parsing but semantic edge networks have also become of interest because of the sparseness of the segmented maps. This work presents an end-to-end trained lightweight deep semantic edge detection architecture called LiteEdge suitable for edge deployment. By utilizing hierarchical supervision and a new weighted multi-label loss function to balance different edge classes during training, LiteEdge predicts with high accuracy category-wise binary edges. Our LiteEdge network with only ≈ 3M parameters, has a semantic edge prediction accuracy of 52.9% mean maximum F (MF) score on the Cityscapes dataset. This accuracy was evaluated on the network trained to produce a low resolution edge map. The network can be quantized to 6-bit weights and 8-bit activations and shows only a 2% drop in the mean MF score. This quantization leads to a memory footprint savings of 6X for an edge device.

Statistics

Citations

Dimensions.ai Metrics
1 citation in Web of Science®
3 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

31 downloads since deposited on 16 Mar 2022
16 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Software
Physical Sciences > Computer Vision and Pattern Recognition
Language:English
Event End Date:17 October 2021
Deposited On:16 Mar 2022 13:35
Last Modified:17 Mar 2022 21:00
Publisher:IEEE
OA Status:Green
Publisher DOI:https://doi.org/10.1109/iccvw54120.2021.00300
  • Content: Published Version
  • Licence: Creative Commons: Attribution 4.0 International (CC BY 4.0)