Thinklab-SJTU/R3Det_Tensorflow
R3Det is a single-stage object detector with feature refinement for detecting rotated objects in aerial and satellite imagery.
Not currently ranked — collecting fresh signals.
star history
This repository implements R3Det and R3Det++, deep learning-based single-stage object detectors published at AAAI 2021. The system uses a Feature Refinement Module (FRM) to iteratively refine detection on oriented objects, supporting datasets like DOTA and HRSC2016. Built on RetinaNet with Focal Loss, it includes techniques such as IoU-Smooth L1 Loss and Circular Smooth Label (CSL) for rotation-aware detection.
Frequently asked
- What is Thinklab-SJTU/R3Det_Tensorflow?
- R3Det is a single-stage object detector with feature refinement for detecting rotated objects in aerial and satellite imagery.
- Is R3Det_Tensorflow open source?
- Yes — Thinklab-SJTU/R3Det_Tensorflow is open source, released under the Apache-2.0 license.
- What language is R3Det_Tensorflow written in?
- Thinklab-SJTU/R3Det_Tensorflow is primarily written in Python.
- How popular is R3Det_Tensorflow?
- Thinklab-SJTU/R3Det_Tensorflow has 546 stars on GitHub.
- Where can I find R3Det_Tensorflow?
- Thinklab-SJTU/R3Det_Tensorflow is on GitHub at https://github.com/Thinklab-SJTU/R3Det_Tensorflow.