English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Artificial intelligence methods show great promise in increasing the qualityand speed of work with large astronomical datasets, but the high complexity ofthese methods leads to the extraction of dataset-specific, non-robust features.Therefore, such methods do not generalize well across multiple datasets. Wepresent a universal domain adaptation method, \textit{DeepAstroUDA}, as anapproach to overcome this challenge. This algorithm performs semi-superviseddomain adaptation and can be applied to datasets with different datadistributions and class overlaps. Non-overlapping classes can be present in anyof the two datasets (the labeled source domain, or the unlabeled targetdomain), and the method can even be used in the presence of unknown classes. Weapply our method to three examples of galaxy morphology classification tasks ofdifferent complexities ($3$-class and $10$-class problems), with anomalydetection: 1) datasets created after different numbers of observing years froma single survey (LSST mock data of $1$ and $10$ years of observations); 2) datafrom different surveys (SDSS and DECaLS); and 3) data from observing fieldswith different depths within one survey (wide field and Stripe 82 deep field ofSDSS). For the first time, we demonstrate the successful use of domainadaptation between very discrepant observational datasets.\textit{DeepAstroUDA} is capable of bridging the gap between two astronomicalsurveys, increasing classification accuracy in both domains (up to $40\%$ onthe unlabeled data), and making model performance consistent across datasets.Furthermore, our method also performs well as an anomaly detection algorithmand successfully clusters unknown class samples even in the unlabeled targetdataset.

DeepAstroUDA: Semi-Supervised Universal Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection