YOLO-CIANNA: Galaxy detection with deep learning in radio data - II. Winning the SKA SDC2 using a generalized 3D-YOLO network

Open Access

Table E.1

SDC2 scores for models trained from a degraded selection function.

Model	M_s (Score)	N_det	N_match	N_false	Purity	$\bar{s}$ $Mathematical equation: $\[\bar{s}\]$$
B-BASE	23 238	34 688	32 031	2664	92.34%	0.8084
B-BT1	24 657	36 548	33 612	2941	91.97%	0.8209
B-BT2	24 978	36 938	33 816	3130	91.55%	0.8310

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.