pith. machine review for the scientific record. sign in

arxiv: 2605.13842 · v1 · submitted 2026-05-13 · 🌌 astro-ph.GA · astro-ph.IM

Recognition: no theorem link

From DES to KiDS: Domain adaptation for cross-survey detection of low-surface-brightness galaxies

Hareesh Thuruthipilly , Krzysztof Lisiecki , Junais , Katarzyna Ma{\l}ek , Agnieszka Pollo , William J. Pearson , Antonio Vanzanella , Saptarshi Pal
show 14 more authors
Miguel Figueira Pratik Dabhade Anna Durkalec Aidan P. Cotter Unnikrishnan Sureshkumar Nandini Hazra Patryk Matera Subhrata Dey Michal Vr\'abel Anirban Dutta Henry Willems Nicola Principi Cavaterra Natalia Dobrowolska Wojciech Knop
Authors on Pith no claims yet

Pith reviewed 2026-05-14 17:42 UTC · model grok-4.3

classification 🌌 astro-ph.GA astro-ph.IM
keywords low-surface-brightness galaxiesdomain adaptationdeep learningKiDS surveyDES surveyultra-diffuse galaxiescross-survey detection
0
0 comments X

The pith

Domain adaptation allows deep learning models trained on DES data to detect low-surface-brightness galaxies in KiDS imaging.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper establishes that models trained on Dark Energy Survey cutouts can be transferred via domain adaptation to identify low-surface-brightness galaxies in Kilo-Degree Survey DR5 data despite differences in depth and seeing. An ensemble of one convolutional neural network and two transformer models applied to KiDS yields 20,180 LSBGs and 434 ultra-diffuse galaxies whose structural parameters align with samples from DES and HSC-SSP. The detected galaxies trace a continuous size-luminosity sequence connecting classical dwarfs to UDGs, display bimodal colors, and show clear environmental dependence in star formation when cross-matched to spectroscopic and cluster catalogs. The work frames this transfer as a practical route to homogeneous LSBG catalogs ahead of LSST and Euclid data volumes.

Core claim

Models trained on DES cutouts and applied through domain adaptation to KiDS DR5 imaging identify 20,180 LSBGs and 434 UDGs whose structural parameters, size-luminosity relation, and color bimodality match known populations from other surveys, with cluster environments linked to redder colors and suppressed star formation.

What carries the argument

Domain adaptation of an ensemble consisting of one convolutional neural network and two transformer models trained on DES cutouts for application to KiDS DR5 imaging.

If this is right

  • 20,180 LSBGs and 434 UDGs are catalogued in KiDS DR5 with structural parameters matching those from DES and HSC-SSP.
  • The LSBGs follow a continuous size-luminosity relation that bridges classical dwarf galaxies and ultra-diffuse galaxies.
  • Cluster LSBGs exhibit redder colors and lower star formation rates than field systems, as shown by spectroscopic cross-matches.
  • The same transfer method supplies a scalable route to uniform LSBG catalogues once LSST and Euclid imaging become available.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same adaptation pipeline could be applied to additional overlapping surveys to enlarge combined LSBG samples for statistical studies.
  • Environmental trends measured here suggest LSBG star-formation histories are shaped by local density, a relation that can be tested with future cluster surveys.
  • Once validated on larger areas, this approach reduces the need for survey-specific retraining and supports automated processing of petabyte-scale datasets.

Load-bearing premise

The models trained on DES generalize to KiDS without large biases from survey differences in depth, seeing, or filters, and the detected objects are genuine LSBGs rather than contaminants.

What would settle it

A blind visual inspection or independent catalog cross-match of a random subset of the 20,180 candidates that reveals systematic differences in detection purity or structural parameters between the two surveys.

Figures

Figures reproduced from arXiv: 2605.13842 by Agnieszka Pollo, Aidan P. Cotter, Anirban Dutta, Anna Durkalec, Antonio Vanzanella, Hareesh Thuruthipilly, Henry Willems, Junais, Katarzyna Ma{\l}ek, Krzysztof Lisiecki, Michal Vr\'abel, Miguel Figueira, Nandini Hazra, Natalia Dobrowolska, Nicola Principi Cavaterra, Patryk Matera, Pratik Dabhade, Saptarshi Pal, Subhrata Dey, Unnikrishnan Sureshkumar, William J. Pearson, Wojciech Knop.

Figure 1
Figure 1. Figure 1: Example RGB images of LSBGs and UDGs created us [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
Figure 4
Figure 4. Figure 4: Mean effective r-band surface brightness as a func￾tion of visual morphology. The sample is divided into unclassi￾fied (25.1 %), featureless (10.1 %), spiral (21.3 %), and elliptical (43.4 %) galaxies. The horizontal lines indicate the median sur￾face brightness for each class. while featureless systems exhibit systematically lower values (n = 0.80). We note that higher spatial resolution imaging may alter… view at source ↗
Figure 3
Figure 3. Figure 3: Distribution of (g−r) colours for the KiDS-LSBG sample. The black step histogram shows the colour distribution, while the green curve represents the best-fitting double Gaussian model. The blue and red dashed curves denote the individual Gaussian components, corresponding to the blue and red LSBG popu￾lations, respectively. The mean (µ) and the standard deviation (σ) of each Gaussian component are shown in… view at source ↗
Figure 5
Figure 5. Figure 5: The size-luminosity relation for the non-UDGs and [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: The estimated photo-z as a function of spectroscopic red￾shift is shown in the left panel. The dashed line indicates the one￾to-one relation, while the vertical error bars represent the photo-z uncertainties. The right panel shows the redshift bias, defined as ∆z = zphot − zspec, as a function of spectroscopic redshift. The red curve denotes the binned median bias, and the shaded re￾gion represents the sca… view at source ↗
Figure 7
Figure 7. Figure 7: SFR as a function of M⋆ for LSBGs. Each panel corre￾sponds to a different redshift bin, indicated in the upper-left cor￾ner. Coloured points represent the LSBGz sample. The median error within the LSBGz sample is shown as a black point. Grey contours show the distribution of LSBGs with photo-z, marking the 95th and 99th percentiles. The red dash-dotted line with red shaded region (±0.4 dex) illustrates the… view at source ↗
Figure 8
Figure 8. Figure 8: Comparison of the stellar mass and star formation rate [PITH_FULL_IMAGE:figures/full_fig_p013_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Quenched fraction (fq) versus median stellar mass for non-UDGs (blue open circles) and UDGs (red filled diamonds) in cluster and non-cluster environments. Different marker sizes indicate distinct redshift bins, increasing with redshift from 0.00 < z ≤ 0.03 to 0.10 < z ≤ 0.20. Quenched galaxies are defined by ∆MSLSBGs < −0.4 dex. 5.5. Quenched LSBGs and UDGs Despite the limitations discussed above, the deri… view at source ↗
read the original abstract

Low-surface-brightness galaxies (LSBGs) are vital for understanding galaxy formation, but their diffuse nature makes them challenging to detect. Upcoming large-scale surveys are expected to uncover large numbers of LSBGs, requiring robust automated methods to identify them across heterogeneous datasets. As a precursor to the Legacy Survey of Space and Time (LSST) and Euclid, we explore domain adaptation techniques for cross-survey LSBG identification. Using models trained on the Dark Energy Survey (DES), we search for LSBGs in the Kilo-Degree Survey Data Release 5 (KiDS DR5). We used an ensemble consisting of one convolutional neural network (CNN) and two transformer models trained on DES cutouts and applied to KiDS DR5 imaging data. Structural parameters were estimated with galfitm, and photometric redshifts and stellar population properties were estimated through spectral energy distribution fitting with CIGALE. We identify 20,180 LSBGs and 434 ultra-diffuse galaxies (UDGs) in KiDS DR5. Their structural parameters are similar to known LSBGs from DES and the Hyper Suprime-Cam SSP Survey (HSC-SSP). The KiDS-LSBGs follow a continuous size-luminosity relation connecting classical dwarf galaxies and UDGs, and their colours are bimodal ($\sim73\%$ blue, $\sim27\%$ red). Cross-matching with spectroscopic and cluster catalogues provides redshifts for 4,913 systems, enabling a systematic characterisation of the star-forming main sequence of LSBGs. Strong environmental trends are evident, with cluster LSBGs and UDGs exhibiting redder colours and reduced star formation compared to non-cluster systems. We demonstrate that domain adaptation enables robust cross-survey LSBG identification with deep learning models, providing a scalable pathway for constructing homogeneous LSBG catalogues for the LSST and Euclid era.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

4 major / 2 minor

Summary. The paper claims that domain adaptation with an ensemble of one CNN and two transformer models trained on DES cutouts can be applied to KiDS DR5 imaging to robustly detect LSBGs, yielding 20,180 LSBGs and 434 UDGs whose galfitm structural parameters and CIGALE-derived properties are consistent with DES and HSC-SSP samples; a subset with spectroscopic redshifts shows expected trends in the star-forming main sequence and environmental effects, demonstrating a scalable pathway for homogeneous LSBG catalogs in the LSST/Euclid era.

Significance. If the generalization claim holds, the work would be significant as a practical demonstration of cross-survey LSBG detection that could enable large, homogeneous samples for future wide-field surveys. The reported sample size, multi-wavelength characterization, and environmental analysis are strengths, and the use of an ensemble plus cross-matching with spectroscopic catalogs provides a concrete starting point for catalog construction.

major comments (4)
  1. [Abstract] Abstract and §3 (implied methods): the domain-adaptation technique itself is not described (no equations, no training details on how DES-to-KiDS shift is mitigated), so it is impossible to evaluate whether differences in depth, seeing, and filter response are actually addressed.
  2. [Abstract] Abstract and Results: no quantitative metrics (precision, recall, contamination fraction, or false-positive rate) are supplied for the KiDS detections; the central claim of 'robust' identification therefore rests only on post-selection similarity of galfitm and CIGALE parameters, which does not directly test model performance on the target domain.
  3. [Results] Results: the reported 20,180 detections and 4,913 spectroscopic redshifts lack error bars, statistical tests for parameter agreement with DES/HSC, or a control sample to quantify selection biases introduced by the domain shift.
  4. [Validation] Validation: no held-out KiDS labeled set or domain-shift simulations are presented, leaving open the possibility that a non-negligible fraction of detections are imaging artifacts rather than genuine LSBGs.
minor comments (2)
  1. [Figures] Figure captions and axis labels for the size-luminosity relation should explicitly state the selection cuts applied to both KiDS and comparison samples.
  2. [Methods] The ensemble architecture (CNN + two transformers) would benefit from a short table summarizing input sizes, training hyperparameters, and inference thresholds.

Simulated Author's Rebuttal

4 responses · 1 unresolved

We thank the referee for their constructive and detailed comments, which have highlighted important areas for clarification and strengthening of the manuscript. We address each major comment below and will revise the paper to incorporate additional details, analyses, and explicit discussions of limitations where feasible.

read point-by-point responses

  1. Referee: [Abstract] Abstract and §3 (implied methods): the domain-adaptation technique itself is not described (no equations, no training details on how DES-to-KiDS shift is mitigated), so it is impossible to evaluate whether differences in depth, seeing, and filter response are actually addressed.

    Authors: We agree that the current description of the domain adaptation procedure is insufficiently detailed for full evaluation. In the revised manuscript we will expand §3 to provide the specific domain-adaptation methods, including any equations or procedures used to mitigate differences in depth, seeing, and filter response, together with the training protocol for the CNN and transformer ensemble. revision: yes

  2. Referee: [Abstract] Abstract and Results: no quantitative metrics (precision, recall, contamination fraction, or false-positive rate) are supplied for the KiDS detections; the central claim of 'robust' identification therefore rests only on post-selection similarity of galfitm and CIGALE parameters, which does not directly test model performance on the target domain.

    Authors: The referee is correct that direct performance metrics on the target domain are not reported. Because no labeled KiDS LSBG validation set exists, precision, recall, and false-positive rates cannot be computed directly. We will revise the text to state this limitation explicitly, to justify the indirect validation via parameter consistency, and to include any available contamination estimates from visual inspection or other proxies. revision: partial

  3. Referee: [Results] Results: the reported 20,180 detections and 4,913 spectroscopic redshifts lack error bars, statistical tests for parameter agreement with DES/HSC, or a control sample to quantify selection biases introduced by the domain shift.

    Authors: We will add Poisson error bars to the reported counts. In the revised results section we will include statistical tests (e.g., Kolmogorov-Smirnov) comparing structural-parameter distributions with the DES and HSC-SSP samples and will introduce a control-sample analysis to quantify selection biases arising from the domain shift. revision: yes

  4. Referee: [Validation] Validation: no held-out KiDS labeled set or domain-shift simulations are presented, leaving open the possibility that a non-negligible fraction of detections are imaging artifacts rather than genuine LSBGs.

    Authors: We acknowledge the absence of a held-out labeled KiDS set. In the revised validation section we will add domain-shift simulations to test model robustness under controlled differences in imaging properties and will discuss the risk of imaging artifacts together with the selection criteria used to reduce them, while noting this as an inherent limitation. revision: partial

standing simulated objections not resolved
  • The absence of a labeled KiDS validation set prevents direct computation of precision, recall, contamination fraction, or false-positive rate on the target domain.

Circularity Check

0 steps flagged

No circularity: empirical application of pre-trained models with independent post-processing validation

full rationale

The paper applies an ensemble of CNN and transformer models (pre-trained on DES) directly to KiDS DR5 cutouts, then measures structural parameters via galfitm and SED properties via CIGALE on the resulting detections. These downstream measurements are independent of the detection step and serve as external checks against DES/HSC samples. No equations, parameter fits, or self-citations are used to derive the central claim; the result is an empirical catalog whose properties are compared to external benchmarks rather than predicted from the training inputs by construction. This is a standard non-circular empirical ML transfer study.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the untested assumption that domain shift between DES and KiDS is small enough for the ensemble to transfer without retraining or heavy fine-tuning. No free parameters, invented entities, or additional axioms are stated in the abstract.

axioms (1)
  • domain assumption Deep-learning models trained on DES cutouts will generalize to KiDS DR5 imaging despite differences in depth, PSF, and filters.
    Implicit in the decision to apply the ensemble directly without reported adaptation steps or performance metrics on KiDS.

pith-pipeline@v0.9.0 · 5752 in / 1291 out tokens · 24694 ms · 2026-05-14T17:42:16.214673+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

300 extracted references · 264 canonical work pages · 115 internal anchors

  1. [1]

    Using mock Low Surface Brightness dwarf galaxies to probe Wide Survey detection capabilities

    Euclid preparation. Using mock Low Surface Brightness dwarf galaxies to probe Wide Survey detection capabilities. arXiv e-prints , keywords =. doi:10.48550/arXiv.2509.13163 , archivePrefix =. 2509.13163 , primaryClass =

    work page doi:10.48550/arxiv.2509.13163

  2. [2]

    arXiv e-prints , keywords =

    Euclid Quick Data Release (Q1) -- Data release overview. arXiv e-prints , keywords =. doi:10.48550/arXiv.2503.15302 , archivePrefix =. 2503.15302 , primaryClass =

    work page doi:10.48550/arxiv.2503.15302

  3. [3]

    Mazurowski , keywords =

    Mateusz Buda and Atsuto Maki and Maciej A. Mazurowski , keywords =. A systematic study of the class imbalance problem in convolutional neural networks , journal =. 2018 , issn =. doi:https://doi.org/10.1016/j.neunet.2018.07.011 , url =

    work page doi:10.1016/j.neunet.2018.07.011 2018

  4. [4]

    Neural Networks , year=

    Early Stopping-But When? , author=. Neural Networks , year=

  5. [5]

    A Highly Consistent Framework for the Evolution of the Star-Forming "Main Sequence" from z~0-6

    A Highly Consistent Framework for the Evolution of the Star-Forming ``Main Sequence'' from z -0.5ex 0-6. , keywords =. doi:10.1088/0067-0049/214/2/15 , archivePrefix =. 1405.2041 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0067-0049/214/2/15 2041

  6. [6]

    , keywords =

    Discovery and analysis of low-surface-brightness galaxies in the environment of NGC 1052. , keywords =. doi:10.1051/0004-6361/202142161 , archivePrefix =. 2110.09527 , primaryClass =

    work page doi:10.1051/0004-6361/202142161

  7. [7]

    , keywords =

    Hybrid-z: Enhancing the Kilo-Degree Survey bright galaxy sample photometric redshifts with deep learning. , keywords =. doi:10.1051/0004-6361/202453576 , archivePrefix =. 2501.01942 , primaryClass =

    work page doi:10.1051/0004-6361/202453576

  8. [8]

    Dust Attenuation Curves in the Local Universe: Demographics and New Laws for Star-forming Galaxies and High-redshift Analogs

    Dust Attenuation Curves in the Local Universe: Demographics and New Laws for Star-forming Galaxies and High-redshift Analogs. , keywords =. doi:10.3847/1538-4357/aabf3c , archivePrefix =. 1804.05850 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4357/aabf3c

  9. [9]

    Impact of stochastic star-formation histories and dust on selecting quiescent galaxies with JWST photometry

    Impact of stochastic star-formation histories and dust on selecting quiescent galaxies with JWST photometry. arXiv e-prints , keywords =. doi:10.48550/arXiv.2509.10117 , archivePrefix =. 2509.10117 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2509.10117

  10. [10]

    Starbursts in and out of the star-formation main sequence

    Starbursts in and out of the star-formation main sequence. , keywords =. doi:10.1051/0004-6361/201732370 , archivePrefix =. 1711.10047 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1051/0004-6361/201732370

  11. [11]

    The Star Forming Main Sequence of Dwarf Low Surface Brightness Galaxies

    The Star-forming Main Sequence of Dwarf Low Surface Brightness Galaxies. , keywords =. doi:10.3847/1538-4357/aa9790 , archivePrefix =. 1710.11236 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4357/aa9790

  12. [12]

    In pursuit of giants. I. The evolution of the dust-to-stellar mass ratio in distant dusty galaxies. , keywords =. doi:10.1051/0004-6361/202038405 , archivePrefix =. 2008.09995 , primaryClass =

    work page doi:10.1051/0004-6361/202038405 2008

  13. [13]

    Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks

    Photometric redshifts for the Kilo-Degree Survey. Machine-learning analysis with artificial neural networks. , keywords =. doi:10.1051/0004-6361/201731942 , archivePrefix =. 1709.04205 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1051/0004-6361/201731942

  14. [14]

    Photometric Redshifts based on standard SED fitting procedures

    Photometric redshifts based on standard SED fitting procedures. , keywords =. doi:10.48550/arXiv.astro-ph/0003380 , archivePrefix =. astro-ph/0003380 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.astro-ph/0003380

  15. [15]

    Long-slit Spectroscopy of Edge-on Low Surface Brightness Galaxies

    Long-slit Spectroscopy of Edge-on Low Surface Brightness Galaxies. , keywords =. doi:10.3847/1538-4357/aa6194 , archivePrefix =. 1702.06026 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4357/aa6194

  16. [16]

    URLhttps://doi.org/ 10.1080/01621459.1995.10476572

    Robert E. Kass and Adrian E. Raftery , title =. Journal of the American Statistical Association , volume =. 1995 , publisher =. doi:10.1080/01621459.1995.10476572 , URL =

    work page doi:10.1080/01621459.1995.10476572 1995

  17. [17]

    , keywords =

    MCXC-II: Second release of the Meta-Catalogue of X-ray detected Clusters of galaxies. , keywords =. doi:10.1051/0004-6361/202449427 , archivePrefix =. 2402.01538 , primaryClass =

    work page doi:10.1051/0004-6361/202449427

  18. [18]

    Correcting for the Effects of Interstellar Extinction

    Correcting for the Effects of Interstellar Extinction. , keywords =. doi:10.1086/316293 , archivePrefix =. astro-ph/9809387 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/316293

  19. [19]

    Mass and environment as drivers of galaxy evolution in SDSS and zCOSMOS and the origin of the Schechter function

    Mass and Environment as Drivers of Galaxy Evolution in SDSS and zCOSMOS and the Origin of the Schechter Function. , keywords =. doi:10.1088/0004-637X/721/1/193 , archivePrefix =. 1003.4747 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/721/1/193

  20. [20]

    The Journal of Open Source Software , year = 2016, month = oct, volume =

    SEP: Source Extractor as a library. The Journal of Open Source Software , year = 2016, month = oct, volume =. doi:10.21105/joss.00058 , adsurl =

    work page doi:10.21105/joss.00058 2016

  21. [21]

    2010, Monthly Notices of the Royal Astronomical Society, 408, 1181, doi: 10.1111/j.1365-2966.2010.17197.x

    Photo-z performance for precision cosmology. , keywords =. doi:10.1111/j.1365-2966.2010.16765.x , archivePrefix =. 0910.5735 , primaryClass =

    work page doi:10.1111/j.1365-2966.2010.16765.x 2010

  22. [22]

    2012 , month = apr, journal =

    CFHTLenS: improving the quality of photometric redshifts with precision photometry. , keywords =. doi:10.1111/j.1365-2966.2012.20468.x , archivePrefix =. 1111.4434 , primaryClass =

    work page doi:10.1111/j.1365-2966.2012.20468.x 2012

  23. [23]

    Star formation and the interstellar medium in low surface brightness galaxies. II. Deep CO observations of low surface brightness disk galaxies. , keywords =. doi:10.48550/arXiv.astro-ph/9804291 , archivePrefix =. astro-ph/9804291 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.astro-ph/9804291

  24. [24]

    Oxygen Abundances in Low Surface Brightness Disk Galaxies

    Oxygen Abundances in Low Surface Brightness Disk Galaxies. , keywords =. doi:10.1086/174049 , archivePrefix =. astro-ph/9311064 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/174049

  25. [25]

    , keywords =

    Galaxy merger challenge: A comparison study between machine learning-based detection methods. , keywords =. doi:10.1051/0004-6361/202348239 , archivePrefix =. 2403.15118 , primaryClass =

    work page doi:10.1051/0004-6361/202348239

  26. [26]

    arXiv e-prints , keywords =

    Fitting the Shadows: Star Formation Scaling Relations in the Low Surface Brightness Regime. arXiv e-prints , keywords =. doi:10.48550/arXiv.2509.20080 , archivePrefix =. 2509.20080 , primaryClass =

    work page doi:10.48550/arxiv.2509.20080

  27. [27]

    , keywords =

    The main sequence of star-forming galaxies across cosmic times. , keywords =. doi:10.1093/mnras/stac3214 , archivePrefix =. 2203.10487 , primaryClass =

    work page doi:10.1093/mnras/stac3214

  28. [28]

    , keywords =

    Ultra-diffuse galaxies in the Kilo-Degree Survey with deep learning. , keywords =. doi:10.1051/0004-6361/202556535 , archivePrefix =. 2509.13910 , primaryClass =

    work page doi:10.1051/0004-6361/202556535

  29. [29]

    and Copin, Y

    Stellar population synthesis at the resolution of 2003. , keywords =. doi:10.1046/j.1365-8711.2003.06897.x , archivePrefix =. astro-ph/0309134 , primaryClass =

    work page doi:10.1046/j.1365-8711.2003.06897.x 2003

  30. [30]

    M., 2000, @doi [ ] 10.1086/309250 , http://adsabs.harvard.edu/abs/2000ApJ...539..718C 539, 718

    A Simple Model for the Absorption of Starlight by Dust in Galaxies. , keywords =. doi:10.1086/309250 , archivePrefix =. astro-ph/0003128 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/309250

  31. [31]

    Galactic

    Galactic Stellar and Substellar Initial Mass Function. , keywords =. doi:10.1086/376392 , archivePrefix =. astro-ph/0304382 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/376392

  32. [32]

    The Messenger , year = 2013, month = dec, volume =

    The VISTA Kilo-degree Infrared Galaxy (VIKING) Survey: Bridging the Gap between Low and High Redshift. The Messenger , year = 2013, month = dec, volume =

    2013

  33. [33]

    CIGALE: a python Code Investigating GALaxy Emission

    CIGALE: a python Code Investigating GALaxy Emission. , keywords =. doi:10.1051/0004-6361/201834156 , archivePrefix =. 1811.03094 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1051/0004-6361/201834156

  34. [34]

    Report of the Dark Energy Task Force

    Report of the Dark Energy Task Force. arXiv e-prints , keywords =. doi:10.48550/arXiv.astro-ph/0609591 , archivePrefix =. astro-ph/0609591 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.astro-ph/0609591

  35. [35]

    Research in Astronomy and Astrophysics , keywords =

    Low Surface Brightness Galaxies from BASS+MzLS with Machine Learning. Research in Astronomy and Astrophysics , keywords =. doi:10.1088/1674-4527/ad3954 , archivePrefix =. 2404.18408 , primaryClass =

    work page doi:10.1088/1674-4527/ad3954

  36. [36]

    , keywords =

    The fifth data release of the Kilo Degree Survey: Multi-epoch optical/NIR imaging covering wide and legacy-calibration fields. , keywords =. doi:10.1051/0004-6361/202346730 , archivePrefix =. 2503.19439 , primaryClass =

    work page doi:10.1051/0004-6361/202346730

  37. [37]

    2024 , eprint=

    The effect of image quality on galaxy merger identification with deep learning , author=. 2024 , eprint=

    2024

  38. [38]

    Olson and Dursun Delen , title=

    David L. Olson and Dursun Delen , title=. doi:10.1007/978-3-540-76917-0 , isbn=

    work page doi:10.1007/978-3-540-76917-0

  39. [39]

    Chandra and ROSAT observations of Abell 194: detection of an X-ray cavity and mapping the dynamics of the cluster

    Chandra and ROSAT Observations of A194: Detection of an X-Ray Cavity and Mapping the Dynamics of the Cluster. , keywords =. doi:10.1088/0004-637X/743/1/59 , archivePrefix =. 1106.3434 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/743/1/59

  40. [40]

    The Pan-STARRS 1 Photometric Reference Ladder, Release 12.0

    The Pan-STARRS 1 Photometric Reference Ladder, Release 12.01. , keywords =. doi:10.1088/0067-0049/205/2/20 , archivePrefix =. 1303.3634 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0067-0049/205/2/20

  41. [41]

    Luminosity Functions of 10 Nearby Clusters of Galaxies. I. Data. , keywords =. doi:10.1086/324731 , adsurl =

    work page doi:10.1086/324731

  42. [42]

    The Pan-STARRS1 Photometric System

    The Pan-STARRS1 Photometric System. , keywords =. doi:10.1088/0004-637X/750/2/99 , archivePrefix =. 1203.0297 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/750/2/99

  43. [43]

    The Pan-STARRS1 Surveys

    The Pan-STARRS1 Surveys. arXiv e-prints , keywords =. doi:10.48550/arXiv.1612.05560 , archivePrefix =. 1612.05560 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1612.05560

  44. [44]

    Photometric Calibration of the First 1.5 Years of the Pan-STARRS1 Survey

    Photometric Calibration of the First 1.5 Years of the Pan-STARRS1 Survey. , keywords =. doi:10.1088/0004-637X/756/2/158 , archivePrefix =. 1201.2208 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/756/2/158

  45. [45]

    The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey

    The Ninth Data Release of the Sloan Digital Sky Survey: First Spectroscopic Data from the SDSS-III Baryon Oscillation Spectroscopic Survey. , keywords =. doi:10.1088/0067-0049/203/2/21 , archivePrefix =. 1207.7137 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0067-0049/203/2/21

  46. [46]

    Astronomical Data Analysis Software and Systems XXV , year = 2017, editor =

    The LSST Data Management System. Astronomical Data Analysis Software and Systems XXV , year = 2017, editor =. doi:10.48550/arXiv.1512.07914 , archivePrefix =. 1512.07914 , primaryClass =

    work page doi:10.48550/arxiv.1512.07914 2017

  47. [47]

    Serbian Astronomical Journal , keywords =

    Large Synoptic Survey Telescope: From Science Drivers To Reference Design. Serbian Astronomical Journal , keywords =. doi:10.2298/SAJ0876001I , adsurl =

    work page doi:10.2298/saj0876001i

  48. [48]

    The Hyper Suprime-Cam Software Pipeline

    The Hyper Suprime-Cam software pipeline. , keywords =. doi:10.1093/pasj/psx080 , archivePrefix =. 1705.06766 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1093/pasj/psx080

  49. [49]

    , keywords =

    MUSE observations of the giant low surface brightness galaxy Malin 1: Numerous HII regions, star formation rate, metallicity, and dust attenuation. , keywords =. doi:10.1051/0004-6361/202347669 , archivePrefix =. 2310.11872 , primaryClass =

    work page doi:10.1051/0004-6361/202347669

  50. [50]

    , eprint =

    The Galaxy Evolution Explorer: A Space Ultraviolet Survey Mission. , keywords =. doi:10.1086/426387 , archivePrefix =. astro-ph/0411302 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/426387

  51. [51]

    2004, MNRAS, 351, 1379, doi: 10.1111/j.1365-2966.2004.07876.x

    The cosmological significance of low surface brightness galaxies found in a deep blind neutral hydrogen survey. , keywords =. doi:10.1111/j.1365-2966.2004.08409.x , archivePrefix =. astro-ph/0409628 , primaryClass =

    work page doi:10.1111/j.1365-2966.2004.08409.x 2004

  52. [52]

    and Finkbeiner, Douglas P

    Measuring Reddening with Sloan Digital Sky Survey Stellar Spectra and Recalibrating SFD. , keywords =. doi:10.1088/0004-637X/737/2/103 , archivePrefix =. 1012.4804 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/737/2/103

  53. [53]

    The Astronomical Journal , abstract =

    Wei Du and Cheng Cheng and Zheng Zheng and Hong Wu , title =. The Astronomical Journal , abstract =. 2020 , month =. doi:10.3847/1538-3881/ab6efb , url =

    work page doi:10.3847/1538-3881/ab6efb 2020

  54. [54]

    The Astrophysical Journal Supplement Series , author =

    The Calibration and Data Products of GALEX. , keywords =. doi:10.1086/520512 , archivePrefix =. 0706.0755 , primaryClass =

    work page doi:10.1086/520512

  55. [55]

    , keywords =

    Hyper Suprime-Cam: Camera dewar design. , keywords =. doi:10.1093/pasj/psx069 , adsurl =

    work page doi:10.1093/pasj/psx069

  56. [56]

    , keywords =

    Hyper Suprime-Cam: System design and verification of image quality. , keywords =. doi:10.1093/pasj/psx063 , adsurl =

    work page doi:10.1093/pasj/psx063

  57. [57]

    , keywords =

    Hyper Suprime-Cam: Filters. , keywords =. doi:10.1093/pasj/psy056 , adsurl =

    work page doi:10.1093/pasj/psy056

  58. [58]

    , keywords =

    The on-site quality-assurance system for Hyper Suprime-Cam: OSQAH. , keywords =. doi:10.1093/pasj/psx079 , adsurl =

    work page doi:10.1093/pasj/psx079

  59. [59]

    Revised Catalog of GALEX Ultraviolet Sources. I. The All-Sky Survey: GUVcat\_AIS. , keywords =. doi:10.3847/1538-4365/aa7053 , archivePrefix =. 1704.05903 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4365/aa7053

  60. [60]

    , keywords =

    PEARLS: Low Stellar Density Galaxies in the El Gordo Cluster Observed with JWST. , keywords =. doi:10.3847/1538-4357/ace343 , archivePrefix =. 2303.04726 , primaryClass =

    work page doi:10.3847/1538-4357/ace343

  61. [61]

    Maps of Dust IR Emission for Use in Estimation of Reddening and CMBR Foregrounds

    Maps of Dust Infrared Emission for Use in Estimation of Reddening and Cosmic Microwave Background Radiation Foregrounds. , keywords =. doi:10.1086/305772 , archivePrefix =. astro-ph/9710327 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/305772

  62. [62]

    The Cosmological Unimportance of Low Surface Brightness Galaxies

    The Cosmological Unimportance of Low Surface Brightness Galaxies. , keywords =. doi:10.1086/497565 , archivePrefix =. astro-ph/0510259 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/497565

  63. [63]

    Multiple Classifier Systems , pages=

    Ensemble methods in machine learning , author=. Multiple Classifier Systems , pages=. 2000 , publisher=

    2000

  64. [64]

    Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining , pages=

    Metacost: a general method for making classifiers cost-sensitive , author=. Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining , pages=. 1999 , organization=

    1999

  65. [65]

    APLpy: Astronomical Plotting Library in Python

  66. [66]

    Color Separation of Galaxy Types in the Sloan Digital Sky Survey Imaging Data

    Color Separation of Galaxy Types in the Sloan Digital Sky Survey Imaging Data. , keywords =. doi:10.1086/323301 , archivePrefix =. astro-ph/0107201 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1086/323301

  67. [67]

    and Wilkinson, M

    Galaxy Zoo: the dependence of morphology and colour on environment*. , keywords =. doi:10.1111/j.1365-2966.2008.14252.x , archivePrefix =. 0805.2612 , primaryClass =

    work page doi:10.1111/j.1365-2966.2008.14252.x 2008

  68. [68]

    International Conference on Learning Representations , year=

    Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models , author=. International Conference on Learning Representations , year=

  69. [69]

    Imfit: A Fast, Flexible New Program for Astronomical Image Fitting

    IMFIT: A Fast, Flexible New Program for Astronomical Image Fitting. , keywords =. doi:10.1088/0004-637X/799/2/226 , archivePrefix =. 1408.1097 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.1088/0004-637x/799/2/226

  70. [70]

    , keywords =

    Dark Energy Survey Year 3 Results: Photometric Data Set for Cosmology. , keywords =. doi:10.3847/1538-4365/abeb66 , archivePrefix =. 2011.03407 , primaryClass =

    work page doi:10.3847/1538-4365/abeb66 2011

  71. [71]

    arXiv e-prints , keywords =

    Paying Attention to Astronomical Transients: Introducing the Time-series Transformer for Photometric Classification. arXiv e-prints , keywords =. doi:10.48550/arXiv.2105.06178 , archivePrefix =. 2105.06178 , primaryClass =

    work page doi:10.48550/arxiv.2105.06178

  72. [72]

    , keywords =

    Deep Attention-based Supernovae Classification of Multiband Light Curves. , keywords =. doi:10.3847/1538-3881/ac9ab4 , archivePrefix =. 2201.08482 , primaryClass =

    work page doi:10.3847/1538-3881/ac9ab4

  73. [73]

    , keywords =

    Detection of Strongly Lensed Arcs in Galaxy Clusters with Transformers. , keywords =. doi:10.3847/1538-3881/aca1c2 , archivePrefix =. 2211.05972 , primaryClass =

    work page doi:10.3847/1538-3881/aca1c2

  74. [74]

    Astronomical CCD Observing and Reduction Techniques , year = 1992, editor =

    Basic Photometry Techniques. Astronomical CCD Observing and Reduction Techniques , year = 1992, editor =

    1992

  75. [75]

    Strong Gravitational Lensing Parameter Estimation with Vision Transformer

    Huang, Kuan-Wei and Chen, Geoff Chih-Fan and Chang, Po-Wen and Lin, Sheng-Chieh and Hsu, ChiaJung and Thengane, Vishal and Lin, Joshua Yao-Yu. Strong Gravitational Lensing Parameter Estimation with Vision Transformer. Computer Vision -- ECCV 2022 Workshops. 2023

    2022

  76. [76]

    Science China Physics, Mechanics, and Astronomy , keywords =

    The FAST all sky H I survey (FASHI): The first release of catalog. Science China Physics, Mechanics, and Astronomy , keywords =. doi:10.1007/s11433-023-2219-7 , archivePrefix =. 2312.06097 , primaryClass =

    work page doi:10.1007/s11433-023-2219-7

  77. [77]

    The Arecibo Legacy Fast ALFA Survey: The ALFALFA Extragalactic HI Source Catalog

    The Arecibo Legacy Fast ALFA Survey: The ALFALFA Extragalactic H I Source Catalog. , keywords =. doi:10.3847/1538-4357/aac956 , archivePrefix =. 1805.11499 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4357/aac956

  78. [78]

    2001, MNRAS, 322, 231, doi: 10.1046/j.1365-8711.2001.04022.x

    The 2dF Galaxy Redshift Survey: spectra and redshifts. , keywords =. doi:10.1046/j.1365-8711.2001.04902.x , archivePrefix =. astro-ph/0106498 , primaryClass =

    work page doi:10.1046/j.1365-8711.2001.04902.x 2001

  79. [79]

    , keywords =

    The Seventeenth Data Release of the Sloan Digital Sky Surveys: Complete Release of MaNGA, MaStar, and APOGEE-2 Data. , keywords =. doi:10.3847/1538-4365/ac4414 , archivePrefix =. 2112.02026 , primaryClass =

    work page doi:10.3847/1538-4365/ac4414

  80. [80]

    Data Release 1 of the Dark Energy Spectroscopic Instrument

    Data Release 1 of the Dark Energy Spectroscopic Instrument. arXiv e-prints , keywords =. doi:10.48550/arXiv.2503.14745 , archivePrefix=. 2503.14745 , primaryClass =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2503.14745

Showing first 80 references.