Deblending galaxy superpositions with branched generative adversarial networks

Reiman, David; Göhre, Brett E

doi:10.1093/mnras/stz575

Cited by 52 publications

(43 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Consequently, several tools also exist to perform deblending as a separate process. As these tools are predominantly either designed to use the results of another source extraction tool (such as SCARLET (Melchior et al 2018), which uses SExtractor for initial source detection), or are predominantly designed for smaller images with only a few galaxies (such as the machine-learning-based methods proposed in Reiman & Göhre (2019)), we chose not to include them in the comparisons in this paper. However, the evaluation process we define in section 3 could equally be used to compare deblending-specific tools.…”

Section: Deblendingmentioning

confidence: 99%

Optimising and comparing source-extraction tools using objective segmentation quality criteria

Haigh

Chamba

Venhola

et al. 2021

A&A

View full text Add to dashboard Cite

Context. With the growth of the scale, depth, and resolution of astronomical imaging surveys, there is increased need for highly accurate automated detection and extraction of astronomical sources from images. This also means there is a need for objective quality criteria, and automated methods to optimise parameter settings for these software tools. Aims. We present a comparison of several tools developed to perform this task: namely SExtractor, ProFound, NoiseChisel, and MTObjects. In particular, we focus on evaluating performance in situations that present challenges for detection. For example, faint and diffuse galaxies; extended structures, such as streams; and objects close to bright sources. Furthermore, we develop an automated method to optimise the parameters for the above tools. Methods. We present four different objective segmentation quality measures, based on precision, recall, and a new measure for the correctly identified area of sources. Bayesian optimisation is used to find optimal parameter settings for each of the four tools when applied to simulated data, for which a ground truth is known. After training, the tools are tested on similar simulated data in order to provide a performance baseline. We then qualitatively assess tool performance on real astronomical images from two different surveys. Results. We determine that when area is disregarded, all four tools are capable of broadly similar levels of detection completeness, while only NoiseChisel and MTObjects are capable of locating the faint outskirts of objects. MTObjects achieves the highest scores on all tests for all four quality measures, whilst SExtractor obtains the highest speeds. No tool has sufficient speed and accuracy to be well suited to large-scale automated segmentation in its current form.

show abstract

Section: Deblendingmentioning

confidence: 99%

Optimising and comparing source-extraction tools using objective segmentation quality criteria

Haigh

Chamba

Venhola

et al. 2021

A&A

View full text Add to dashboard Cite

show abstract

“…Falling within the generation and reconstruction category (Section 2.2), GANs are likely to be the next most significant machine learning approach for astronomy. Early applications of GANs include generating dark matter structures in cosmological simulations (Diakogiannis et al, 2019;Rodríguez et al, 2018), the creation of realistic images of galaxies as an input to weak gravitational lensing analysis (Fussell & Moews, 2019), and deblending overlaps between foreground and background galaxies in highly crowded images (Reiman & Göhre, 2019).…”

Section: Techniquesmentioning

confidence: 99%

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy

Fluke

Jacobs

2019

WIREs Data Min & Knowl

105

View full text Add to dashboard Cite

Machine learning (automated processes that learn by example in order to classify, predict, discover, or generate new data) and artificial intelligence (methods by which a computer makes decisions or discoveries that would usually require human intelligence) are now firmly established in astronomy. Every week, new applications of machine learning and artificial intelligence are added to a growing corpus of work. Random forests, support vector machines, and neural networks are now having a genuine impact for applications as diverse as discovering extrasolar planets, transient objects, quasars, and gravitationally lensed systems, forecasting solar activity, and distinguishing between signals and instrumental effects in gravitational wave astronomy. This review surveys contemporary, published literature on machine learning and artificial intelligence in astronomy and astrophysics. Applications span seven main categories of activity: classification, regression, clustering, forecasting, generation, discovery, and the development of new scientific insights. These categories form the basis of a hierarchy of maturity, as the use of machine learning and artificial intelligence emerges, progresses, or becomes established. This article is categorized under: Application Areas > Science and Technology Fundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining Technologies > Machine Learning

show abstract

“…Katmanların ince ayarı içinde denetimli öğrenme modeli kullanılmıştır. Her bir katmanda denetimsiz öğrenme için [19] [25], fotoğraf çözünürlüğünü arttırma [26], gerçek zamanlı kişi konum analizi [27], fotoğraf açıklama [28], fotoğraftaki insanların bakışlarında değişiklik yapma [29], gerçek zamanlı davranış analizi [30], fotoğraflardan yeni fotoğraf oluşturma [31], galaksi ve yanardağ resimleri oluşturma [32,33] görüntü alanındaki derin öğrenme çalışmalarına örnek verilebilmektedir. Bununla birlikte farklı diller arasında çeviride de derin öğrenme kullanılmaktadır [34].…”

Section: Derin öğRenme Yöntemlerinin Uygulanma Alanlarıunclassified

Sağlık Alanında Kullanılan Derin Öğrenme Yöntemleri

Kaya

Yilmaz

Dikmen

2019

European Journal of Science and Technology

View full text Add to dashboard Cite

Öz Uzun süreli tedavi gerektiren kanser ve benzeri hastalıklara yakalanan hastaların ölüm riski yüksektir. Bu riski azaltmak ve hastanın yaşam süresini uzatmak için tıpta, teknolojideki gelişmelerin de kullanıldığı çalışmalar bulunmaktadır. Bu çalışmalarda hastalığın tedavisi için çok önemli olan erken tanı yöntemlerine odaklanılmıştır. Yapay zekâ, makinelerin insan beyninin çalışmasını taklit ederek karar verme ve tahmin etme gibi çözülmesi zor olan problemlerin çözümüne imkân tanıyan bir bilim dalıdır. Yapay zekânın bir alt dalı olan makine öğrenmesi ise kodlanmış olan hazır talimatları kullanarak çözüm üretmek yerine; örneklerden öğrenerek, görüntü, resim ve ses tanıma gibi birçok zor probleme çözüm getirmektedir. Son yıllarda birçok alanda kullanılan makine öğrenmesinin, hastalıkların erken teşhisinde kullanılabilme potansiyeli de bulunmaktadır. Konu ile ilgili yapılan çalışmalar özellikle makine öğrenmesinin bir alt dalı olan derin öğrenme yöntemlerine odaklanmıştır. Bu çalışmanın amacı sağlık alanında uygulanan derin öğrenme yöntemlerinin çalışma prensiplerini ve hangi hastalıklarda kullanıldığını, ilgili literatür ışığında ortaya koymaktır. Bu çalışmanın sonucunda, hastalığın teşhisinde kullanılan verilere uygun derin öğrenme yönteminin tercih edilmesinin, hastalığa erken tanı konma başarısını arttıracağı düşünülmektedir.

show abstract

Deblending galaxy superpositions with branched generative adversarial networks

Cited by 52 publications

References 32 publications

Optimising and comparing source-extraction tools using objective segmentation quality criteria

Optimising and comparing source-extraction tools using objective segmentation quality criteria

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy

Sağlık Alanında Kullanılan Derin Öğrenme Yöntemleri

Contact Info

Product

Resources

About