T²Det: Twin-tower detector with geometric invariance for oriented object detection

Introduction

This repository is the official implementation of "T²Det: Twin-tower detector with geometric invariance for oriented object detection" at [Please stay tuned!]

The master branch is built on MMRotate which works with PyTorch 1.8+.

T²Det's train/test configure files are placed under configs/exp_configs/t2det/

The Instructions of T²Det can be referenced to here.

Deep Learning Experiments

Source of Pre-trained models

• CSPNeXt-m: pre-trained checkpoint supported by Openmmlab(link).
• ResNet: pre-trained ResNet50 supported by Pytorch.

Results and models

1. VEDAI

Model	mAP	Angle	lr schd	Batch Size	Configs	Download
RTMDet-M	83.32	le90	6x	4		model
T2Det	85.15	le90	6x	4	t2det-vedai	model |log

2. HRSC2016

Model	mAP	Angle	lr schd	Batch Size	Configs	Download
T2Det	90.66	le90	6x	8	t2det-hrsc2016	model | log

For example, when dataset is VEDAI and method is T²Det, you can train by running the following

python tools/train.py \
  --config configs/exp_configs/t2det/VEDAI/t2det_rtmdet_m-6x-vedai.py \
  --work-dir work_dirs/t2det \
  --load_from path/to/pre-trained/model \

and if you want test the VEDAI results, you can run as follows

python tools/test.py \
  --config configs/exp_configs/t2det/VEDAI/t2det_rtmdet_m-6x-vedai.py \
  --checkpoint path/to/t2det/model.pth \
  --cfg-options test_evaluator.outfile_prefix='path/to/save_dir'

Hyperparameters Configuration

Detailed hyperparameters config can be found in t2det_configs

Installation

MMRotate depends on PyTorch, MMCV and MMDetection. Below are quick steps for installation. Please refer to Install Guide for more detailed instruction.

conda create --name openmmlab python=3.8 -y
conda activate openmmlab
conda install pytorch==1.8.0 torchvision==0.9.0 cudatoolkit=10.2 -c pytorch
pip install -U openmim
mim install mmcv-full
mim install mmdet
git clone https://github.com/Qian-CV/PG-DRFNet.git
cd PG-DRFNet
pip install -v -e .

Get Started

Please see here for the basic usage of MMRotate. We also provide some tutorials for:

• learn the basics
• learn the config
• customize dataset
• customize model
• tutorial of T²Det
• useful tools

Acknowledgments

The code is developed based on the following repositories. We appreciate their nice implementations.

Method	Repository
RTMDet	https://github.com/open-mmlab/mmdetection
RTMDet-R	https://github.com/open-mmlab/mmrotate
ECANet	https://github.com/BangguWu/ECANet
QFocal	https://github.com/implus/GFocal

Cite this repository

If you use this software in your work, please cite it using the following metadata. Liuqian Wang, Jing Zhang, et. al. (2024). T²Det by BJUT-AI&VBD [Computer software]. https://github.com/Qian-CV/T2Det.git