Advanced International Journal for Research

E-ISSN: 3048-7641   •   Impact Factor: 9.11

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 1 (January-February 2026) Submit your research before last 3 days of February to publish your research paper in the issue of January-February.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 1
January-February 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar UTeM - Universiti Teknikal Malaysia Melaka Wiki for Call for Papers WorldCat Zenodo

Understanding Image Resolution Sensitivity in Modern YOLO Architectures

Author(s) Mr. Ketan Kanjiya, Mr. Piyush Sonani, Mr. Upendrasinh Zala
Country India
Abstract Input image resolution plays a critical yet often underexplored role in the performance and efficiency of modern object detection systems. While YOLO architectures support flexible input sizes, models are typically trained at fixed resolutions, making resolution selection a key deployment decision. This paper presents a systematic investigation of image resolution sensitivity in YOLOv11 across multiple model scales. Using the Aerial Sheep dataset, five YOLOv11 variants (Nano to Extra Large) are fine-tuned at three training resolutions 320×320, 640×640, and 1280×1280 under identical training conditions. Detection performance is evaluated using mAP@50, mAP@50-95, precision, and recall, alongside a detailed analysis of inference latency. Results demonstrate that input resolution is a dominant factor influencing detection accuracy, often exceeding the impact of model scaling. Substantial performance gains are observed when increasing resolution from 320×320 to 640×640, while improvements beyond 640×640 show diminishing returns for coarse detection metrics. Inference analysis reveals that model size and training resolution primarily govern runtime, with inference time resolution and image content exerting secondary effects. These findings provide practical guidance for balancing accuracy and efficiency in real-world YOLO deployments.
Keywords Yolo, Object Detection, Image Resolution, Deep Learning, Image Resolution Sensitivity
Field Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In Volume 7, Issue 1, January-February 2026
Published On 2026-02-07
View / Download PDF File

Share this



E-ISSN 3048-7641
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 1Cover Page Vol 6 Isu 6Cover Page Vol 6 Isu 5

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AIJFR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9898-79-39-59 editor@aijfr.com