Benchmark and Model Zoo (To be updated)

• Rotated RetinaNet-OBB/HBB (ICCV’2017)

• Rotated FasterRCNN-OBB (TPAMI’2017)

• Rotated RepPoints-OBB (ICCV’2019)

• Rotated FCOS (ICCV’2019)

• RoI Transformer (CVPR’2019)

• Gliding Vertex (TPAMI’2020)

• Rotated ATSS-OBB (CVPR’2020)

• CSL (ECCV’2020)

• R³Det (AAAI’2021)

• S²A-Net (TGRS’2021)

• ReDet (CVPR’2021)

• Beyond Bounding-Box (CVPR’2021)

• Oriented R-CNN (ICCV’2021)

• GWD (ICML’2021)

• KLD (NeurIPS’2021)

• SASM (AAAI’2022)

• Oriented RepPoints (CVPR’2022)

• KFIoU (arXiv)

• H2RBox (arXiv)

Results on DOTA v1.0

Backbone	mAP	Angle	lr schd	Mem (GB)	Inf Time (fps)	Aug	Batch Size	Configs	Download
ResNet50 (1024,1024,200)	59.44	oc	1x	3.45	15.6	-	2	rotated-reppoints-qbox_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	64.55	oc	1x	3.38	15.7	-	2	rotated-retinanet-hbox-oc_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	65.59	oc	1x	3.12	18.5	-	2	rotated_atss_hbb_r50_fpn_1x_dota_oc	model | log
ResNet50 (1024,1024,200)	66.45	oc	1x	3.53	15.3	-	2	sasm-reppoints-qbox_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	68.42	le90	1x	3.38	16.9	-	2	rotated-retinanet-rbox-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	68.79	le90	1x	2.36	22.4	-	2	rotated-retinanet-rbox-le90_r50_fpn_amp-1x_dota	model | log
ResNet50 (1024,1024,200)	69.49	le135	1x	4.05	8.6	-	2	g_reppoints_r50_fpn_1x_dota_le135	model | log
ResNet50 (1024,1024,200)	69.51	le90	1x	4.40	24.0	-	2	rotated-retinanet-rbox-le90_r50_fpn_csl-gaussian_amp-1x_dota	model | log
ResNet50 (1024,1024,200)	69.55	oc	1x	3.39	15.5	-	2	rotated-retinanet-hbox-oc_r50_fpn_gwd_1x_dota	model | log
ResNet50 (1024,1024,200)	69.60	le90	1x	3.38	15.1	-	2	rotated-retinanet-hbox-le90_r50_fpn_kfiou_1x_dota	model | log
ResNet50 (1024,1024,200)	69.63	le135	1x	3.45	16.1	-	2	cfa-qbox_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	69.76	oc	1x	3.39	15.6	-	2	rotated-retinanet-hbox-oc_r50_fpn_kfiou_1x_dota	model | log
ResNet50 (1024,1024,200)	69.77	le135	1x	3.38	15.3	-	2	rotated-retinanet-hbox-le135_r50_fpn_kfiou_1x_dota	model | log
ResNet50 (1024,1024,200)	69.79	le135	1x	3.38	17.2	-	2	rotated-retinanet-rbox-le135_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	69.80	oc	1x	3.54	12.4	-	2	r3det-oc_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	69.94	oc	1x	3.39	15.6	-	2	rotated-retinanet-hbox-oc_r50_fpn_kld_1x_dota	model | log
ResNet50 (1024,1024,200)	70.18	oc	1x	3.23	15.6	-	2	r3det-tiny-oc_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	70.64	le90	1x	3.12	18.2	-	2	rotated_atss_obb_r50_fpn_1x_dota_le90	model | log
ResNet50 (1024,1024,200)	70.70	le90	1x	4.18		-	2	rotated-fcos-hbox-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	71.28	le90	1x	4.18		-	2	rotated-fcos-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	71.76	le90	1x	4.23		-	2	rotated-fcos-hbox-le90_r50_fpn_csl-gaussian_1x_dota	model | log
ResNet50 (1024,1024,200)	71.83	oc	1x	3.54	12.4	-	2	r3det-oc_r50_fpn_kld-stable_1x_dota	model | log
ResNet50 (1024,1024,200)	71.89	le90	1x	4.18		-	2	rotated-fcos-le90_r50_fpn_kld_1x_dota	model | log
ResNet50 (1024,1024,200)	71.94	le135	1x	3.45	16.1	-	2	oriented-reppoints-qbox_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	72.29	le135	1x	3.19	18.8	-	2	rotated_atss_obb_r50_fpn_1x_dota_le135	model | log
ResNet50 (1024,1024,200)	72.68	oc	1x	3.62	12.2	-	2	r3det-oc_r50_fpn_kfiou-ln_1x_dota	model | log
ResNet50 (1024,1024,200)	72.76	oc	1x	3.44	14.0	-	2	r3det-tiny-oc_r50_fpn_kld_1x_dota	model | log
ResNet50 (1024,1024,200)	73.23	le90	1x	8.45	16.4	-	2	gliding-vertex-rbox_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	73.40	le90	1x	8.46	16.5	-	2	rotated-faster-rcnn-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	73.45	oc	40e	3.45	16.1	-	2	cfa-qbox_r50_fpn_40e_dota	model | log
ResNet50 (1024,1024,200)	73.91	le135	1x	3.14	15.5	-	2	s2anet-le135_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	74.19	le135	1x	2.17	17.4	-	2	s2anet-le135_r50_fpn_amp-1x_dota	model | log
ResNet50 (1024,1024,200)	75.63	le90	1x	7.37	21.2	-	2	oriented-rcnn-le90_r50_fpn_amp-1x_dota	model | log
ResNet50 (1024,1024,200)	75.69	le90	1x	8.46	16.2	-	2	oriented-rcnn-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,200)	75.75	le90	1x	7.56	19.3	-	2	roi-trans-le90_r50_fpn_amp-1x_dota	model | log
ReResNet50 (1024,1024,200)	75.99	le90	1x	7.71	13.3	-	2	redet-le90_re50_refpn_amp-1x_dota	model | log
ResNet50 (1024,1024,200)	76.08	le90	1x	8.67	14.4	-	2	roi-trans-le90_r50_fpn_1x_dota	model | log
ResNet50 (1024,1024,500)	76.50	le90	1x		17.5	MS+RR	2	rotated-retinanet-rbox-le90_r50_fpn_rr-1x_dota-ms	model | log
ReResNet50 (1024,1024,200)	76.68	le90	1x	9.32	10.9	-	2	redet-le90_re50_refpn_1x_dota	model | log
Swin-tiny (1024,1024,200)	77.51	le90	1x		10.9	-	2	roi-trans-le90_swin-tiny_fpn_1x_dota	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
ReResNet50 (1024,1024,500)	79.87	le90	1x		10.9	MS+RR	2	redet-le90_re50_refpn_rr-1x_dota-ms	model | log
ResNet50 (1024,1024,200)	68.75	le90	1x	6.25		-	2	h2rbox-le90_r50_fpn_adamw-1x_dota	model | log

• MS means multiple scale image split.

• RR means random rotation.

The above models are trained with 1 * 1080Ti/2080Ti and inferred with 1 * 2080Ti.