چکیده مقاله
Feature Pyramid Networks FPN have become a standard multi scale representation for modern visual recognition This review consolidates core FPN design principles top down pathways, lateral fusion, and scale aware heads and synthesizes recent variants such as BiFPN, PANet/PAFPN, ssFPN, Refine FPN, and attention guided fusion We examine how these necks integrate with common backbones and detectors, summarize typical training setups and datasets e g , COCO, DOTA, SIRST , and report qualitative benefits frequently claimed in the literature, including improved small object sensitivity, faster convergence, and better robustness to scale variance Beyond natural images, we highlight applications in specialized domains remote sensing, infrared, underwater , noting when patterns plausibly translate to medical image analysis A functional comparison of representative detectors clarifies pipeline choices, loss designs, and computational trade offs We conclude with open challenges reliable gains across backbones, practical deployment under resource constraints, and standardized evaluation for domain transfer and provide curated tables that connect variants to tasks, detectors, and the corresponding canonical references
کلیدواژهها
نویسندگان
Milad Soltani
Department of Computer Engineering, Islamic Azad University, Mashhad, Iran
Mohammadamir Razmi
Department of Aerospace Engineering, IAU Science and Research Branch, Tehran, Iran
Pouya Faridfar
Department of Computer Engineering, IAU Mashhad Branch, Mashhad, Iran
شیوه ارجاع
Soltani، Milad و Razmi، Mohammadamir و Faridfar، Pouya،1404،Exploring Variants of Feature Pyramid Networks (FPN) for Object Detection: A Comprehensive Review،یازدهمین کنفرانس بین المللی مهندسی صنایع و سیستم ها،مشهد
ارائهشده در
مجموعه مقالات یازدهمین کنفرانس بین المللی مهندسی صنایع و سیستم ها2 مهر 1404 · مشهد