In this paper, we present an effective Dynamic Enhancement Anchor (DEA) network to construct a novel training sample generator. Different from other state-of-the-art techniques, the proposed network leverages a sample discriminator to realize interactive sample screening between an anchor-based unit and an anchor-free unit to generate eligible samples. Besides, multi-task joint training with a conservative anchor-based inference scheme enhances the performance of the proposed model while suppressing computational complexity. The proposed scheme supports both oriented and horizontal object detection tasks. Extensive experiments on two challenging aerial benchmarks (i.e., DOTA and HRSC2016) indicate that our method achieves state-of-the-art performance in accuracy with moderate inference speeds and computational overhead for training.
This codebase is created to build benchmarks for object detection in aerial images. It is modified from mmdetection. The master branch works with PyTorch 1.1 or higher. If you would like to use PyTorch 0.4.1, please checkout to the pytorch-0.4.1 branch.
Visualization results for oriented object detection on the test set of DOTA.
Comparison to the baseline on DOTA for oriented object detection. The figures with blue boxes are the results of the baseline and pink boxes are the results of our proposed DEA-Net.
ImageNet Pretrained Model from Pytorch
- ResNet50
- ResNet101
- ResNet152
- You can find the detailed configs in configs/DOTA.
- The trained models are available at Google Drive
Please refer to INSTALL.md for installation.
Please see GETTING_STARTED.md for the basic usage of mmdetection.
We appreciate all contributions to improve benchmarks for object detection in aerial images.