PANOPTICON: A novel deep learning model to detect single transit events with no prior data filtering in PLATO light curves

Open Access

Fig. A.2

Architecture of Unet++ of the same depth as Fig. A.1. This version introduces a more complex recombination during decoding. Each encoding level is upsampled individually and combined in nested dense skip connections. This gives a better merging of various feature sizes when creating the output.

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.