0% Complete
صفحه اصلی
/
سی و دومین کنفرانس بین المللی مهندسی برق
Bag of Freebies Techniques to Improve Face Detection Accuracy for Small Faces
نویسندگان :
Nahid Seyed Ebrahimian
1
Azadeh Ashouri
2
Reza Akhoundzade
3
Mohammad Reza Mohammadi
4
1- دانشگاه فردوسی مشهد
2- دانشگاه فردوسی مشهد
3- دانشگاه صنعتی شریف
4- دانشگاه علم و صنعت ایران
کلمات کلیدی :
Face Detection،SCRFD،YOLOv5-Face،Deep Learning،Convolutional Neural Networks
چکیده :
Face detection is a primary and essential task in the domain of face recognition and identification, serving as the initial and crucial step in the process. There are several models for face detection, such as RetinaFace, Yolov5-Face, and SCRFD. The best model can vary based on specific criteria such as accuracy, speed, memory efficiency, and suitability for different applications. Among these face detection models, the SCRFD model has the most optimal trade-off between speed and accuracy, which makes it a popular and suitable model for face detection applications. However, in the real world, extracting meaningful features and detecting small faces in surveillance videos can be challenging due to the low resolution. In this research, we focus on enhancing the accuracy of the SCRFD(Sample and Computation Redistribution for Efficient Face Detection) model on small faces. We conduct a comprehensive enhancement using multiple strategies, including expanding the dataset, adjusting input shape during training time, tuning weight decay, optimizing the learning rate scheduler, and testing different augmentations. By analyzing these factors systematically, we achieved mAP of 69.88% and 85.23% at 640 × 640 and 1280 × 1280 resolutions respectively in the Hard dataset, which outperforms the original SCRFD by 0.39% and 1.58٪.
لیست مقالات
لیست مقالات بایگانی شده
The Use of Additive Decomposition and Deep Neural Network for Photovoltaic Power Forecasting
Fariba Dehghan - Mohsen Parsa Moghaddam - Maryam Imani
A Hybrid Data-Driven Algorithm for Real-Time Friction Force Estimation in Hydraulic Cylinders
Mohamad Amin Jamshidi - Mehrbod Zarifi - Zolfa Anvari - Hamed Ghafarirad - Mohammad Zareinejad
A High Linearity Wideband Low-Noise Amplifier Using Capacitor Cross-Coupled Common-Gate Structure
Abolfazl Rajaiyan - Fahimeh Rahimi - Mehdi Saberi
Reduction of Common-Mode Voltage in Cascaded H-Bridge Inverter Under Faulty Conditions
Ashkan Raki - Yousef Neyshabouri - Hossein Iman-Eini - Mahdi Aslanian
An Iterative Approach to Enhance the Accuracy of TDOA-Based Localization by Averaging and Reducing Noise
Reza Bahrampour - Mohammad Hossein Madani - Hossein Bahramgiri
Global Voltage Harmonic Index for Measuring Harmonic Situation of Power Grids: A Focus on Power Transformers
Alireza Zabihi - Mehrzad Bidari - Hossein Mokhtari
Security and Privacy Smart Contract Architecture for Energy Trading based on Blockchains
Masoumeh Nazari - Siavash Khorsandi - Jaber Babaki
Design of an Optical Current Transformer for High-Voltage Gas-Insulated Switchgear-Part II: Focus on GIS Compartment Design
Reza Babaei - Asghar Akbari - Arash Moradi
Weak GPS Signal Acquisition Based on Wavelet Transform Denoising and Deep Learning Method
Navid Moradi - Mohsen Nezhadshahbodaghi - Mohammad-Reza Mosavi
An Event-Triggered Robust Data-Driven Predictive Control with Transient Response Improvement
Amir Mehrnoosh - Mohammad Haeri
بیشتر
ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.5.3