Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Yue Zhou 5f7d50d27c | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
metafile.yml | 2 years ago | |
roi_trans_r50_fpn_1x_dota_le90.py | 2 years ago | |
roi_trans_r50_fpn_1x_dota_le135.py | 2 years ago | |
roi_trans_r50_fpn_1x_dota_ms_le90.py | 1 year ago | |
roi_trans_r50_fpn_1x_dota_ms_rr_le90.py | 2 years ago | |
roi_trans_r50_fpn_1x_dota_oc.py | 2 years ago | |
roi_trans_r50_fpn_fp16_1x_dota_le90.py | 2 years ago | |
roi_trans_swin_tiny_fpn_1x_dota_le90.py | 2 years ago |
Learning RoI Transformer for Oriented Object Detection in Aerial Images
Object detection in aerial images is an active yet challenging task in computer vision because of the bird’s-eye view perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed objects in aerial images, methods relying on horizontal proposals for common object detection often introduce mismatches between the Region of Interests (RoIs) and objects. This leads to the common misalignment between the final object classification confidence and localization accuracy. In this paper, we propose a RoI Transformer to address these problems. The core idea of RoI Transformer is to apply spatial transformations on RoIs and learn the transformation parameters under the supervision of oriented bounding box (OBB) annotations. RoI Transformer is with lightweight and can be easily embedded into detectors for oriented object detection. Simply apply the RoI Transformer to light-head RCNN has achieved state-of-the-art performances on two common and challenging aerial datasets, i.e., DOTA and HRSC2016, with a neglectable reduction to detection speed. Our RoI Transformer exceeds the deformable Position Sensitive RoI pooling when oriented bounding-box annotations are available. Extensive experiments have also validated the flexibility and effectiveness of our RoI Transformer
DOTA1.0
Backbone | mAP | Angle | lr schd | Mem (GB) | Inf Time (fps) | Aug | Batch Size | Configs | Download |
---|---|---|---|---|---|---|---|---|---|
ResNet50 (1024,1024,200) | 73.40 | le90 | 1x | 8.46 | 16.5 | - | 2 | rotated_faster_rcnn_r50_fpn_1x_dota_le90 | model | log |
ResNet50 (1024,1024,200) | 75.75 | le90 | 1x | 7.56 | 19.3 | - | 2 | roi_trans_r50_fpn_fp16_1x_dota_le90 | model | log |
ResNet50 (1024,1024,200) | 76.08 | le90 | 1x | 8.67 | 14.4 | - | 2 | roi_trans_r50_fpn_1x_dota_le90 | model | log |
Swin-tiny (1024,1024,200) | 77.51 | le90 | 1x | 10.9 | - | 2 | roi_trans_swin_tiny_fpn_1x_dota_le90 | model | log | |
ResNet50 (1024,1024,500) | 79.66 | le90 | 1x | 14.4 | MS+RR | 2 | roi_trans_r50_fpn_1x_dota_ms_rr_le90 | model | log |
Notes:
MS
means multiple scale image split.RR
means random rotation.@InProceedings{ding2018learning,
author = {Ding, Jian and Xue, Nan and Long, Yang and Xia, Gui-Song and Lu, Qikai},
title = {Learning RoI Transformer for Oriented Object Detection in Aerial Images},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition},
pages={2849--2858},
year = {2019}
}
No Description
Python Markdown Dockerfile Shell other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》