README.md

KFIoU

The KFIoU Loss for Rotated Object Detection

Abstract

Differing from the well-developed horizontal object detection area whereby the computing-friendly IoU based loss is readily adopted and well fits with the detection metrics. In contrast, rotation detectors often involve a more complicated loss based on SkewIoU which is unfriendly to gradient-based training. In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss instead of the strict value-level identity. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU by its definition, and show its alignment with the SkewIoU at trend-level. This is in contrast to recent Gaussian modeling based rotation detectors e.g. GWD, KLD that involves a human-specified distribution distance metric which requires additional hyperparameter tuning. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU, thanks to its full differentiability and ability to handle the non-overlapping cases. We further extend our technique to the 3-D case which also suffers from the same issues as 2-D detection. Extensive results on various public datasets (2-D/3-D, aerial/text/face images) with different base detectors show the effectiveness of our approach.

Results and models

DOTA1.0

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	Aug	Batch Size	Configs	Download
ResNet50 (1024,1024,200)	64.55	oc	1x	3.38	15.7	-	2	rotated_retinanet_hbb_r50_fpn_1x_dota_oc	model | log
ResNet50 (1024,1024,200)	69.60	le90	1x	3.38	15.1	-	2	rotated_retinanet_hbb_kfiou_r50_fpn_1x_dota_le90	model | log
ResNet50 (1024,1024,200)	69.76	oc	1x	3.39	15.6	-	2	rotated_retinanet_hbb_kfiou_r50_fpn_1x_dota_oc	model | log
ResNet50 (1024,1024,200)	69.77	le135	1x	3.38	15.3	-	2	rotated_retinanet_hbb_kfiou_r50_fpn_1x_dota_le135	model | log

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	Aug	Batch Size	Configs	Download
ResNet50 (1024,1024,200)	69.80	oc	1x	3.54	12.4	-	2	r3det_r50_fpn_1x_dota_oc	model | log
ResNet50 (1024,1024,200)	72.68	oc	1x	3.62	12.2	-	2	r3det_kfiou_ln_r50_fpn_1x_dota_oc	model | log

Citation

@misc{yang2022kfiou,
      title={The KFIoU Loss for Rotated Object Detection},
      author={Xue Yang and Yue Zhou and Gefan Zhang and Jirui Yang and Wentao Wang and Junchi Yan and Xiaopeng Zhang and Qi Tian},
      year={2022},
      eprint={2201.12558},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}