Xinbin Yuan, Zhaohui Zheng, YuXuan Li, Xialei Liu, Li Liu, Xiang Li, Qibin Hou, Ming-Ming Cheng
While witnessed with rapid development, remote sensing object detection remains challenging for detecting high aspect ratio objects. This paper shows that large strip convolutions are good feature representation learners for remote sensing object detection and can detect objects of various aspect ratios well. Based on large strip convolutions, we build a new network architecture called Strip R-CNN, which is simple, efficient, and powerful. Unlike recent remote sensing object detectors that leverage large-kernel convolutions with square shapes, our Strip R-CNN takes advantage of sequential orthogonal large strip convolutions to capture spatial information. In addition, we enhance the localization capability of remote-sensing object detectors by decoupling the detection heads and equipping the localization head with strip convolutions to better localize the target objects. Extensive experiments on several benchmarks, e.g., DOTA, FAIR1M, HRSC2016, and DIOR, show that our Strip R-CNN can largely improve previous works. Notably, our 30M model achieves 82.75% mAP on DOTA-v1.0, setting a new state-of-the-art record.Code is available at https://github.com/YXB-NKU/Strip-R-CNN.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Object Detection | HRSC2016 | mAP-07 | 90.6 | Strip R-CNN |
| Object Detection | HRSC2016 | mAP-12 | 98.7 | Strip R-CNN |
| 3D | HRSC2016 | mAP-07 | 90.6 | Strip R-CNN |
| 3D | HRSC2016 | mAP-12 | 98.7 | Strip R-CNN |
| 2D Classification | HRSC2016 | mAP-07 | 90.6 | Strip R-CNN |
| 2D Classification | HRSC2016 | mAP-12 | 98.7 | Strip R-CNN |
| 2D Object Detection | HRSC2016 | mAP-07 | 90.6 | Strip R-CNN |
| 2D Object Detection | HRSC2016 | mAP-12 | 98.7 | Strip R-CNN |
| 16k | HRSC2016 | mAP-07 | 90.6 | Strip R-CNN |
| 16k | HRSC2016 | mAP-12 | 98.7 | Strip R-CNN |