Skip to content

axionl/MASF-YOLO

BranchesTags
 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
ultralytics
ultralytics
 
 
README.md
README.md
 
 
best_s.pt
best_s.pt
 
 

Repository files navigation

MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View

MASF-YOLO is an enhanced object detection network based on YOLOv11, specifically designed for small object detection in UAV imagery.arXiv:https://arxiv.org/abs/2504.18136

MASF-YOLO Architecture

Contributions

Multi-scale Feature Aggregation Module (MFAM)

image

Improved Efficient Multi-scale Attention(IEMA)

图片1

Dimension-Aware Selective Integration Module(DASI)

图片2

Dataset

https://github.com/VisDrone/VisDrone-Dataset

Environment

  • CUDA Version: 11.3
  • GPU: NVIDIA GeForce RTX 4090D 24G

Training configuration

  • Optimizer: SGD
  • Batch Size: 12
  • Total Epochs: 100
  • Image Size: 640×640

For complete training configuration and implementation details, please refer to the train.py

Ablation Study

image
image

Comparison With State-of-the-Arts

image

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 89.5%
  • Jupyter Notebook 4.4%
  • C++ 2.3%
  • Rust 2.3%
  • CMake 0.3%
  • JavaScript 0.3%
  • Other 0.9%