YOLO-CIANNA: Galaxy detection with deep learning in radio data - I. A new YOLO-inspired source detection method applied to the SKAO SDC1

Open Access

Table C.1

Scores and related properties based on the alternative training area for source catalogs from different models.

Method	M_s (Score)	N_det	N_match	N_false	N_bad ∈ N_false	Purity	$\bar{s}$ $\bar s$
YOLO-CIANNA-alt-train-large-bootstrap	502656	723655	690894	32761	12991	95.47%	0.7750
YOLO-CIANNA-alt-train-large	486053	709689	674404	35285	14380	95.02%	0.7730
YOLO-CIANNA-alt-train	484145	708954	672906	36048	14988	94.91%	0.7731

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.