MMRotate: A Rotated Object Detection Benchmark using PyTorch

By Yue Zhou, Xue Yang, Gefan Zhang, Jiabao Wang, Yanyi Liu, Liping Hou, Xue Jiang, Xingzhao Liu, Junchi Yan, Chengqi Lyu and 2 more. ACM Multimedia, 2022

454 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5df51cc8f6cb3f6e63164099013a3b4878254dc9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Gong Cheng
3. Qi Tian
4. Luc Van Gool
5. Junchi Yan
6. Wangmeng Zuo
7. Dacheng Tao
8. Ling Shao

Citations in the corpus

• Localization Distillation for Object Detection (2022, methodology): “We follow the mmRotate [81] training and testing protocols.”
• Large Selective Kernel Network for Remote Sensing Object Detection (2023, methodology): “The models are implemented under MMRotate [88] framework.”
• RTMDet: An Empirical Study of Designing Real-Time Object Detectors (2022, methodology): “Code and models of RTMDet-R are released at MMRotate [99].”
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss (2021, background): “The source codes [70, 84] are made public available.”
• Poly Kernel Inception Network for Remote Sensing Detection (2024, methodology): “See §4.2 for details. tings of previous methods [21, 65, 71, 78], we crop the original images into 1024 × 1024 patches with overlaps of 200 for DOTA-v1.”
• Towards Large-Scale Small Object Detection: Survey and Benchmarks (2022, methodology): “To conduct fair comparisons of several benchmarking base-lines, all the experiments on SODA-D and SODA-A are implemented on top of the toolbox mmdetection 5 [171] and mm-rotate 6 [172], respectively.”