MMRotate: A Rotated Object Detection Benchmark using PyTorch
This work addresses the need for a standardized benchmark and toolkit in rotated object detection, facilitating research and industrial applications in this domain.
The authors introduced MMRotate, an open-source toolbox for rotated object detection, implementing 18 state-of-the-art algorithms and supporting three angle definition methods to provide a coherent framework for training, inference, and evaluation.
We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning. MMRotate implements 18 state-of-the-art algorithms and supports the three most frequently used angle definition methods. To facilitate future research and industrial applications of rotated object detection-related problems, we also provide a large number of trained models and detailed benchmarks to give insights into the performance of rotated object detection. MMRotate is publicly released at https://github.com/open-mmlab/mmrotate.