Mining for Strong Gravitational Lenses with Self-supervised Learning

Stein, George; Blaum, Jacqueline; Harrington, Peter de B.; Medan, Tomislav; Lukić, Zarija

doi:10.3847/1538-4357/ac6d63

Cited by 24 publications

(13 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hayat et al (2021) showed indeed that, by using the latent space for morphological classification of galaxies, they can reach a similar accuracy as with a fully supervised CNN but using >10 times less labelled data. In the follow-up work by Stein et al (2021a), they also explore how the self-supervised representations can be used to find strong gravitational lenses reaching similar conclusions. Similarly to the work by Cheng et al (2020), the representations are used with a small sample of lenses to train a simple linear classifier and find new strong lenses candidates.…”

Section: Visualisation Of Large Datasetsmentioning

confidence: 99%

“…An additional way to identify outliers is through the representation space learned by contrastive learning, as one would do with a latent space from an Autoeconder. Stein et al (2021b) explored this approach on images from the DESI survey and demonstrated the efficiency of self-supervised representations to identify outliers and perform similarity searches. See also the work by Walmsley et al (2021) which uses the tools developed by Lochner & Bassett (2021) for similarity search and anomaly detection on the representation spaces.…”

Section: Deep Learning For Discoverymentioning

confidence: 99%

See 1 more Smart Citation

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

Huertas-Company

Lanusse²

2023

Publ. Astron. Soc. Aust.

View full text Add to dashboard Cite

The amount and complexity of data delivered by modern galaxy surveys has been steadily increasing over the past years. New facilities will soon provide imaging and spectra of hundreds of millions of galaxies. Extracting coherent scientific information from these large and multi-modal data sets remains an open issue for the community and data-driven approaches such as deep learning have rapidly emerged as a potentially powerful solution to some long lasting challenges. This enthusiasm is reflected in an unprecedented exponential growth of publications using neural networks, which have gone from a handful of works in 2015 to an average of one paper per week in 2021 in the area of galaxy surveys. Half a decade after the first published work in astronomy mentioning deep learning, and shortly before new big data sets such as Euclid and LSST start becoming available, we believe it is timely to review what has been the real impact of this new technology in the field and its potential to solve key challenges raised by the size and complexity of the new datasets. The purpose of this review is thus two-fold. We first aim at summarising, in a common document, the main applications of deep learning for galaxy surveys that have emerged so far. We then extract the major achievements and lessons learned and highlight key open questions and limitations, which in our opinion, will require particular attention in the coming years. Overall, state-of-the-art deep learning methods are rapidly adopted by the astronomical community, reflecting a democratisation of these methods. This review shows that the majority of works using deep learning up to date are oriented to computer vision tasks (e.g. classification, segmentation). This is also the domain of application where deep learning has brought the most important breakthroughs so far. However, we also report that the applications are becoming more diverse and deep learning is used for estimating galaxy properties, identifying outliers or constraining the cosmological model. Most of these works remain at the exploratory level though which could partially explain the limited impact in terms of citations. Some common challenges will most likely need to be addressed before moving to the next phase of massive deployment of deep learning in the processing of future surveys; for example, uncertainty quantification, interpretability, data labelling and domain shift issues from training with simulations, which constitutes a common practice in astronomy.

show abstract

Section: Visualisation Of Large Datasetsmentioning

confidence: 99%

Section: Deep Learning For Discoverymentioning

confidence: 99%

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

Huertas-Company

Lanusse²

2023

Publ. Astron. Soc. Aust.

View full text Add to dashboard Cite

show abstract

“…In [54] this same technique was used to construct representations for CWoLa-based anomaly detection. In addition to these works, other self-supervised / representation learning techniques have been applied in particle physics [55,56] and in other scientific disciplines such as astrophysics [57][58][59][60]. In [53,54] the augmentations corresponded to transformations of the event to which the underlying physics should be invariant to rotations or translations, but also soft-collinear parton splittings.…”

Section: Introductionmentioning

confidence: 99%

Anomalies, Representations, and Self-Supervision

Dillon¹,

Favaro²,

Feiden³

et al. 2023

Preprint

View full text Add to dashboard Cite

We develop a self-supervised method for density-based anomaly detection using contrastive learning, and test it using event-level anomaly data from CMS ADC2021. The Anomaly-CLR technique is data-driven and uses augmentations of the background data to mimic non-Standard-Model events in a model-agnostic way. It uses a permutation-invariant Transformer Encoder architecture to map the objects measured in a collider event to the representation space, where the data augmentations define a representation space which is sensitive to potential anomalous features. An AutoEncoder trained on background representations then computes anomaly scores for a variety of signals in the representation space. With AnomalyCLR we find significant improvements on performance metrics for all signals when compared to the raw data baseline.

show abstract

“…The key principle is to extract underlying patterns in data by maximizing similarities of augmentations from the same instances while minimizing the similarity of different instances 31 . Recently, contrastive learning has attracted increasing attention in the natural sciences and has shown remarkable results on a variety of scienti c problems, including molecular representation 40,41 , density-of-states of 2D photonic crystals 42 , similarity search for sky surveys 43 , single-particle diffraction images 44 , and Raman spectrum. In particular, Ref.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Approaches to the Classification of Spectra: Application to Phase Transitions in X-ray Diffraction Data

Sun

Brockhauser

Hegedűs

et al. 2023

Preprint

View full text Add to dashboard Cite

The ability to detect interesting events is instrumental to effectively steer experiments and maximize their scientific efficiency. To address this, here we introduce and validate three frameworks based on self-supervised learning which are capable of classifying 1D spectral data using a limited amount of labeled data. In particular, in this work we focus on the identification of phase transitions in samples investigated by x-ray diffraction. We demonstrate that the three frameworks, based either on relational reasoning, contrastive learning, or a combination of the two, are capable of accurately identifying phase transitions. Furthermore, we discuss in detail the selection of data augmentations, crucial to ensure that scientifically meaningful information is retained.

show abstract

Mining for Strong Gravitational Lenses with Self-supervised Learning

Cited by 24 publications

References 53 publications

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

The Dawes Review 10: The impact of deep learning for the analysis of galaxy surveys

Anomalies, Representations, and Self-Supervision

Self-Supervised Approaches to the Classification of Spectra: Application to Phase Transitions in X-ray Diffraction Data

Contact Info

Product

Resources

About