The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution.With the upcoming Large-scale Imaging Surveys,billions of galaxy images challenge astronomers to accomplish the classification task by applying traditional methods or human inspection.Consequently,machine learning,in particular supervised deep learning,has been widely employed to classify galaxy morphologies recently due to its exceptional automation,efficiency,and accuracy.However,supervised deep learning requires extensive training sets,which causes considerable workloads;also,the results are strongly dependent on the characteristics of training sets,which leads to biased outcomes potentially.In this study,we attempt Few-shot Learning to bypass the two issues.Our research adopts the data set from the Galaxy Zoo Challenge Project on Kaggle,and we divide it into five categories according to the corresponding truth table.By classifying the above data set utilizing few-shot learning based on Siamese Networks and supervised deep learning based on AlexNet,VGG_16,and ResNet_50 trained with different volumes of training sets separately,we find that few-shot learning achieves the highest accuracy in most cases,and the most significant improvement is 21％compared to AlexNet when the training sets contain 1000 images.In addition,to guarantee the accuracy is no less than 90％,few-shot learning needs～6300 images for training,while ResNet_50 requires～13,000 images.Considering the advantages stated above,foreseeably,few-shot learning is suitable for the taxonomy of galaxy morphology and even for identifying rare astrophysical objects,despite limited training sets consisting of observational data only.

Zhirui Zhang;Zhiqiang Zou;Nan Li;Yanli Chen

College of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210023,China;Jiangsu Key Laboratory of Big Data Security and Intelligent Processing,Nanjing 210023,China;Key Laboratory of Optical Astronomy,National Astronomical Observatories,Chinese Academy of Sciences,Beijing 100101,China;University of Chinese Academy of Sciences,Beijing 100049,China

天文和天体物理学研究

[1]Zhirui Zhang;Zhiqiang Zou;Nan Li;Yanli Chen-.Classifying Galaxy Morphologies with Few-shot Learning)[J].天文和天体物理学研究,2022(05):9-20

astronomers,foreseeably

Classifying,Galaxy,Morphologies,Few,shot,Learning,taxonomy,galaxy,morphology,critical,astrophysics,morphological,properties,powerful,tracers,evolution,With,upcoming,Large,scale,Imaging,Surveys,billions,images,challenge,accomplish,classification,task,applying,traditional,methods,human,inspection,Consequently,machine,learning,particular,supervised,deep,has,been,widely,employed,morphologies,recently,due,its,exceptional,automation,efficiency,accuracy,However,requires,extensive,training,sets,which,causes,considerable,workloads,also,results,strongly,dependent,characteristics,leads,biased,outcomes,potentially,In,this,study,attempt,bypass,issues,Our,research,adopts,data,from,Zoo,Challenge,Project,Kaggle,divide,into,five,categories,according,corresponding,truth,By,classifying,above,utilizing,few,Siamese,Networks,AlexNet,VGG,ResNet,trained,different,volumes,separately,find,that,achieves,highest,most,cases,significant,improvement,compared,when,contain,addition,guarantee,less,than,needs,while,Considering,advantages,stated,suitable,even,identifying,rare,astrophysical,objects,despite,limited,consisting,observational,only

0.597162