Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Infrared Domain Adaptation with Zero-Shot Quantization
Download
Burak_Sevsay_MSc_Thesis.pdf
Date
2024-9-03
Author
Sevsay, Burak
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
6
views
4
downloads
Cite This
Object detection models are gaining popularity in daily life and industry, increasing the demand for real-time computation of these models. Model compression is an essential technique to achieve faster inference and smaller footprints. Quantization is a widely used model compression technique, reducing bit-width and enhancing efficiency at the cost of quantization error. Methods like post-training quantization and quantization-aware training require training data to minimize this error. However, training data may be inaccessible due to privacy concerns in applications such as surveillance and autonomous driving. In such cases, zero-shot quantization becomes necessary, as it applies quantization without the need for training data. Additionally, infrared imagery, which is more resilient to illumination and weather conditions, is often a part of these applications. To the best of our knowledge, zero-shot quantization in the infrared domain has not been investigated before. This thesis adapts batch normalization statistics-based zero-shot quantization for the infrared domain. This method aims to generate synthetic data by utilizing batch normalization statistics. We thoroughly investigated the data generation process to achieve optimal results for YOLOv8 and RetinaNet. For infrared adaptation, we fine-tuned models that were pretrained on RGB images using infrared images. The evaluation is based on comparing zero-shot quantization results with those from both full-precision models and post-training quantization. Additionally, we examined the effect of model size on zero-shot quantization. Our results show that batch normalization statistics-based zero-shot quantization is more effective in the infrared domain and is an essential method when training data is unavailable.
Subject Keywords
Data-free Quantization
,
Infrared Domain
,
Object Detection
URI
https://hdl.handle.net/11511/111352
Collections
Graduate School of Informatics, Thesis
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
B. Sevsay, “Infrared Domain Adaptation with Zero-Shot Quantization,” M.S. - Master of Science, Middle East Technical University, 2024.