Please use this identifier to cite or link to this item:
Title: A benchmark of CNN backbones on DINO-DETR performance in object detection
Authors: Liew, Zon Hur Zhen
Keywords: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2023
Publisher: Nanyang Technological University
Source: Liew, Z. H. Z. (2023). A benchmark of CNN backbones on DINO-DETR performance in object detection. Final Year Project (FYP), Nanyang Technological University, Singapore.
Project: SCSE22-0660 
Abstract: 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 on MS-COCO and SODA-D. The results affirm many conclusions from the ConvNeXt and FocalNet papers while exhibiting inconsistencies for FocalNets on SODA-D. Finally, the results show encouraging performance for DINO-DETR with recent backbones on general object detection and the need for further improvement on small object detection with DINO-DETR across all backbones. Further efforts should be made to integrate state-of-the-art features from concurrent developments to produce new benchmarks on small object detection datasets with accessible existing technology.
Schools: School of Computer Science and Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
Undergraduate project report4.7 MBAdobe PDFView/Open

Page view(s)

Updated on Dec 7, 2023


Updated on Dec 7, 2023

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.