Table 7.

Experimental results for the compared state-of-the-art methods on the brain-tumor dataset. The optimal results are marked in bold.

Method	mAP	mAP50	mAP75	mAP(small)	mAP(medium)	mAP(large)
Baseline	0.142	0.270	0.137	0.006	0.181	0.126
Faster RCNN	0.150	0.227	0.188	0.048	0.178	0.126
DINO	0.288	0.430	0.377	0.202	0.333	0.386
Ours	0.314	0.468	0.345	0.161	0.373	0.608