SJTU-Thinklab-Det/DOTA-DOAI
A two-stage object detection codebase for aerial imagery competitions using FPN and ResNet backbones, focused on DOTA remote-sensing datasets.
Not currently ranked — collecting fresh signals.
star history
This repository contains the codebase used by the SJTU-Thinklab-Det team for participating in DOTA-related competitions, which focus on object detection in aerial and remote-sensing imagery. The primary approach uses FPN-based two-stage detectors with ResNet backbones for both rotation and horizontal detection tasks. The project is connected to broader rotation detection benchmarks including MMRotate-Pytorch and AlphaRotate-TF, and reports performance metrics (mAP) on the DOTA1.0 dataset.
Frequently asked
- What is SJTU-Thinklab-Det/DOTA-DOAI?
- A two-stage object detection codebase for aerial imagery competitions using FPN and ResNet backbones, focused on DOTA remote-sensing datasets.
- Is DOTA-DOAI open source?
- Yes — SJTU-Thinklab-Det/DOTA-DOAI is open source, released under the MIT license.
- What language is DOTA-DOAI written in?
- SJTU-Thinklab-Det/DOTA-DOAI is primarily written in Jupyter Notebook.
- How popular is DOTA-DOAI?
- SJTU-Thinklab-Det/DOTA-DOAI has 799 stars on GitHub.
- Where can I find DOTA-DOAI?
- SJTU-Thinklab-Det/DOTA-DOAI is on GitHub at https://github.com/SJTU-Thinklab-Det/DOTA-DOAI.