A benchmark of CNN backbones on DINO-DETR performance in object detection

A benchmark of CNN backbones on DINO-DETR performance in object detection

Recent developments in DETR-based models have made significant improvements in training convergence but not small object detection. This paper combines the ConvNeXt and FocalNet backbones with DINO-DETR using timm and detrex, and presents a benchmark and analysis of the resulting model performances...

Full description

Bibliographic Details
Main Author: Liew, Zon Hur Zhen
Other Authors: Lu Shijian
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2023
Subjects:
Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Online Access:https://hdl.handle.net/10356/172020

Internet

https://hdl.handle.net/10356/172020

Similar Items