Data

Tools

Indexes

Applications

Experiments

Open Source Science

improved-yolov8s

The baseline YOLOv8s model has been improved with the integration of Global Attention Mechanism (GAM), Modified Neck, and Wise Intersection over Union (WIoUv3)

https://github.com/arojsubedi/improved-yolov8s

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

The baseline YOLOv8s model has been improved with the integration of Global Attention Mechanism (GAM), Modified Neck, and Wise Intersection over Union (WIoUv3)

Basic Info
  • Host: GitHub
  • Owner: arojsubedi
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 948 KB
Statistics
  • Stars: 22
  • Watchers: 1
  • Forks: 8
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

Improved YOLOv8s Object Detection Algorithm

Detailed explanation: https://arxiv.org/abs/2412.14211

BibTex Citation: @misc{subedi2024improvinggeneralizationperformanceyolov8, title={Improving Generalization Performance of YOLOv8 for Camera Trap Object Detection}, author={Aroj Subedi}, year={2024}, eprint={2412.14211}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2412.14211}, }

The baseline YOLOv8s model has been improved with the integration of Global Attention Mechanism (GAM), Modified Neck, and Wise Intersection over Union (WIoUv3).

  1. WIoUv3 integration is present in the following files: ultralytics/nn/utils/loss.py, ultralytics/nn/utils/metrics.py, ultralytics/nn/utils/tal.py

  2. Global Attention Mechanism (GAM) module is present in the : ultralytics/nn/modules/attention.py

  3. Additional changes to incorporate files are present in: ultralytics/nn/modules/init.py

  4. Additional changes to facilitate operations are present in: ultralytics/nn/tasks.py

  5. YAML source file: ultralytics/cfg/models/v8/yolov8-GAM-Attention.yaml

Please reach out to me at arojsubedi@gmail.com if you need any help with this repository.

Owner

  • Name: Aroj Subedi
  • Login: arojsubedi
  • Kind: user
  • Location: Cincinnati

Citation (CITATION.cff) 

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use this software, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  - family-names: Chaurasia
    given-names: Ayush
    orcid: "https://orcid.org/0000-0002-7603-6750"
  - family-names: Qiu
    given-names: Jing
    orcid: "https://orcid.org/0000-0003-3783-7069"
  title: "Ultralytics YOLO"
  version: 8.0.0
  # doi: 10.5281/zenodo.3908559  # TODO
  date-released: 2023-1-10
  license: AGPL-3.0
  url: "https://github.com/ultralytics/ultralytics"

GitHub Events

Total
  • Watch event: 21
  • Push event: 2
  • Fork event: 2
Last Year
  • Watch event: 21
  • Push event: 2
  • Fork event: 2