Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
Tedja, Haidhi Angkawijana
Unknown Affiliation
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Performance and Efficiency Comparison of U-Net and Ghost U-Net in Road Crack Segmentation with Floating Point and Quantization Optimization Tedja, Haidhi Angkawijana; Onno W. Purbo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 6 (2024): December 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i6.6089

Abstract

This study presents a comprehensive comparison of U-Net and Ghost U-Net for road crack segmentation, emphasizing their performance and memory efficiency across various data representation formats, including FP32, FP16, and INT8 quantization. A dataset of 12,480 images was used, with preprocessing steps such as binarization and normalization to improve segmentation accuracy. Results show that Ghost U-Net achieved a marginally higher performance, with an IoU of 0.5041 and a Dice coefficient of 0.6664, compared to U-Net’s IoU of 0.5034 and Dice coefficient of 0.6662. Ghost U-Net also demonstrated significant memory efficiency, reducing GPU usage by up to 60% in FP16 and INT8 formats. However, a sharp decline in performance was observed for Ghost U-Net in the INT8 format, where the IoU dropped to 0.2038 and the Dice coefficient to 0.3227, whereas U-Net maintained stable performance across all formats. These findings suggest that Ghost U-Net is preferable for applications prioritizing memory efficiency and inference speed, while U-Net may be better suited for tasks requiring consistent accuracy across different quantization levels. This study underscores the importance of considering both performance stability and memory efficiency when selecting models for deployment in real-world applications.
Co-Authors Onno W. Purbo