Detecting the edges of galaxies with deep learning

Open Access

Table 1

Results for the base experiment.

Encoder	Dice	Precision	Recall
ResNet18	0.8849	0.8531	0.9438
ResNet50	0.8832	0.8340	0.9591
EfficientNetBl	0.8867	0.8543	0.9461
EfficientNetB2	0.8867	0.8437	0.9475
EfficientNetB6	0.8809	0.8604	0.9351
DenseNet161	0.8926	0.8768	0.9316
DenseNet201	0.8867	0.8592	0.9397
Average value	0.8851	0.8545	0.9433

Notes. Last row shows the average values for all encoders. Dice, precision, and recall values are represented in reddish, bluish, and greenish tones respectively, where lighter colors represent higher values and darker colors represent lower values.

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.