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 B.1

SDC1 scores and related properties for source catalogs from different models and architectures.

Method	M_s (Score)	N_det	N_match	N_false	N_bad ∈ N_false	Purity	$\bar{s}$ $\bar s$
darknet-19-regul-scratch	445093	688112	645626	42486	15070	93.83%	0.7552
darknet-19-base-pretrain	423077	665304	620685	44619	16003	93.29%	0.7535
darknet-19-regul-pretrain	411541	642153	600193	41960	13398	93.47%	0.7556
darknet-19-base-scratch	386395	644371	591039	53332	15020	91.72%	0.7440

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.