Data

Tools

Indexes

Applications

Experiments

Open Source Science

unihead

This is the repository for TNNLS paper: "Unihead: unifying multi-perception for detection heads"

https://github.com/zht8506/unihead

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 (7.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

This is the repository for TNNLS paper: "Unihead: unifying multi-perception for detection heads"

Basic Info
  • Host: GitHub
  • Owner: zht8506
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 6.02 MB
Statistics
  • Stars: 14
  • Watchers: 4
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

UniHead: an effective detection head

:loudspeaker: Introduction

This is the official implementation of our paper titled "UniHead: Unifying Multi-Perception for Detection Heads".

For more details, please refer to our paper. This repo is based on PyTorch>=1.7.1 and mmdet==2.25.1.

:trophy: Result

Our UniHead can bring significant AP improvements to a large number of detectors, even with lower model complexity.

New!!! We evaluate our UniHead on the VOC07+12 dataset. We find that our UniHead is also effective, demonstrating the generalization ability of UniHead.

:openfilefolder: Weight

We release the weight of models used in our paper, including RetinaNet, FCOS, RepPoints, FreeAnchor, ATSS and GFL. You may need to log out of your Google account to download them.

Download the weight(s) from corresponding links below. - RetinaNet-UniHead (39.2 AP): Google Drive; BaiduNetDisk

The weights of UniHead with various of backbones (R101 and SwinT) are also released. If you need more models, such as UniHead-SwinB, please feel free to contact me via email.

🚀 Training

More detail please see mmdetection. bash dist_train_UniHead.sh

:ferris_wheel: Visualization

Examples of detection results obtained by our UniHead and baseline (RetinaNet).

📚 Citation

Please cite our work if you find our work and codes helpful for your research. @article{zhou2024unihead, title={Unihead: unifying multi-perception for detection heads}, author={Zhou, Hantao and Yang, Rui and Zhang, Yachao and Duan, Haoran and Huang, Yawen and Hu, Runze and Li, Xiu and Zheng, Yefeng}, journal={IEEE Transactions on Neural Networks and Learning Systems}, year={2024}, publisher={IEEE} }

Acknowledgement

This project is built upon numerous previous projects. We'd like to thank the contributors of mmdetection.

Owner

  • Name: zht8506
  • Login: zht8506
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMDetection Contributors"
title: "OpenMMLab Detection Toolbox and Benchmark"
date-released: 2018-08-22
url: "https://github.com/open-mmlab/mmdetection"
license: Apache-2.0

GitHub Events

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