arXiv subjects

Svyatoslav Voloshynovskiy

Publications and source records attributed to Svyatoslav Voloshynovskiy.

9 recordsLinked to original sources

arXiv2026

DINOspec: Efficient Multimodal Alignment of Vision and Spectral Foundation Models for Astronomy

Astronomical observations provide multimodal views of physical systems, with images and spectra capturing complementary properties of celestial objects. Scientific foundation models can learn powerful representations from these observations, but representations learned by separate models remain difficult to combine. We investigate whether physical representations learned by separate vision and spectral models can be aligned without retraining their encoders. We introduce DINOspec, a multimodal framework that aligns a frozen DINOv3 image encoder with a pre-trained AION-1 spectral tokenizer using lightweight adapters and contrastive learning on 20,472 paired images and spectra of astronomical objects. DINOspec improves galaxy morphology classification (F1: 0.72$\rightarrow$0.78) and spectral classification (F1: 0.70$\rightarrow$0.74) while training at most 21M parameters. Improvements depend on the downstream task, revealing asymmetric transfer between independently learned representations, while spectroscopic redshift prediction remains unchanged ($R^2\approx0.9$). These results demonstrate that scientific foundation models can be composed through lightweight representation alignment.

astro-ph.IM↗

arXiv2026

Learning Radio Astronomical Representations with LeJEPA and Very Small Models

Representations learned by vision foundation models pretrained on natural images have been shown to be useful for out-of-domain astronomical images. Performance on scientific downstream tasks increases with model size, which both carries higher inference costs and limits scalability, even when considering parameter-efficient adaptation. An alternative is to learn representations directly from astronomical observations rather than natural images, through self-supervised pretraining. We evaluate LeJEPA's ability to learn robust representations using very small vision models ($\sim$6M parameters) pretrained on Radio Galaxy Zoo images, comparing with established self-supervised frameworks. We test whether LeJEPA's latent-space regularization leads to better radio galaxy morphology classification. Across three evaluation datasets, LeJEPA achieves performance comparable to a substantially larger foundation model while producing more consistent representations across training and evaluation datasets. These results suggest that the choice of representation learning objective is critical for enabling small domain-specific models to achieve performance competitive with representations transferred from large foundation models in scientific imaging.

astro-ph.IM↗

arXiv2025

TRANSIT your events into a new mass: Fast background interpolation for weakly-supervised anomaly searches

We introduce a new model for conditional and continuous data morphing called TRansport Adversarial Network for Smooth InTerpolation (TRANSIT). We apply it to create a background data template for weakly-supervised searches at the LHC. The method smoothly transforms sideband events to match signal region mass distributions. We demonstrate the performance of TRANSIT using the LHC Olympics R\&D dataset. The model captures non-linear mass correlations of features and produces a template that offers a competitive anomaly sensitivity compared to state-of-the-art transport-based template generators. Moreover, the computational training time required for TRANSIT is an order of magnitude lower than that of competing deep learning methods. This makes it ideal for analyses that iterate over many signal regions and signal models. Unlike generative models, which must learn a full probability density distribution, i.e., the correlations between all the variables, the proposed transport model only has to learn a smooth conditional shift of the distribution. This allows for a simpler, more efficient residual architecture, enabling mass uncorrelated features to pass the network unchanged while the mass correlated features are adjusted accordingly. Furthermore, we show that the latent space of the model provides a set of mass decorrelated features useful for anomaly detection without background sculpting.

hep-ph↗

arXiv2024

Self-Supervised Learning on MeerKAT Wide-Field Continuum Images

Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in models that are adaptable to many different tasks. Until now, applications of SSL to astronomical images have been limited to Galaxy Zoo datasets, which require a significant amount of pre-processing to prepare sparse images centered on a single galaxy. With wide-field survey instruments at the forefront of the Square Kilometer Array (SKA) era, this approach to gathering training data is impractical. We demonstrate that continuum images from surveys like the MeerKAT Galactic Cluster Legacy Survey (MGCLS) can be successfully used with SSL, without extracting single-galaxy cutouts. Using the SSL framework DINO, we experiment with various preprocessing steps, augmentations, and architectures to determine the optimal approach for this data. We train both ResNet50 and Vision Transformer (ViT) backbones. Our models match state-of-the-art results (trained on Radio Galaxy Zoo) for FRI/FRII morphology classification. Furthermore, they predict the number of compact sources via linear regression with much higher accuracy. However, fine-tuning results in similar performance between our models, the state-of-the-art, and open-source models on multi-class morphology classification. Using source-rich crops from wide-field images to train multi-purpose models is an easily scalable approach that significantly reduces data preparation time. For the tasks evaluated in this work, twenty thousand crops is sufficient training data for models that produce results similar to state-of-the-art. In the future, complex tasks like source detection and characterization, together with domain-specific tasks, ought to demonstrate the true advantages of training models with radio astronomy data over natural-image foundation models.

astro-ph.IM↗

arXiv2024

Magnetogram-to-Magnetogram: Generative Forecasting of Solar Evolution

Investigating the solar magnetic field is crucial to understand the physical processes in the solar interior as well as their effects on the interplanetary environment. We introduce a novel method to predict the evolution of the solar line-of-sight (LoS) magnetogram using image-to-image translation with Denoising Diffusion Probabilistic Models (DDPMs). Our approach combines "computer science metrics" for image quality and "physics metrics" for physical accuracy to evaluate model performance. The results indicate that DDPMs are effective in maintaining the structural integrity, the dynamic range of solar magnetic fields, the magnetic flux and other physical features such as the size of the active regions, surpassing traditional persistence models, also in flaring situation. We aim to use deep learning not only for visualisation but as an integrative and interactive tool for telescopes, enhancing our understanding of unexpected physical events like solar flares. Future studies will aim to integrate more diverse solar data to refine the accuracy and applicability of our generative model.

astro-ph.SR↗

arXiv2024

Cluster Scanning: a novel approach to resonance searches

We propose a new model-independent method for new physics searches called Cluster Scanning. It uses the k-means algorithm to perform clustering in the space of low-level event or jet observables, and separates potentially anomalous clusters to construct a signal-enriched region. The spectra of a selected observable (e.g. invariant mass) in these two regions are then used to determine whether a resonant signal is present. A pseudo-analysis on the LHC Olympics dataset with a $Z'$ resonance shows that Cluster Scanning outperforms the widely used 4-parameter functional background fitting procedures, reducing the number of signal events needed to reach a $3σ$ significant access by a factor of 0.61. Emphasis is placed on the speed of the method, which allows the test statistic to be calibrated on synthetic data.

hep-ph↗

arXiv2021

ScatSimCLR: self-supervised contrastive learning with pretext task regularization for small-scale datasets

In this paper, we consider a problem of self-supervised learning for small-scale datasets based on contrastive loss between multiple views of the data, which demonstrates the state-of-the-art performance in classification task. Despite the reported results, such factors as the complexity of training requiring complex architectures, the needed number of views produced by data augmentation, and their impact on the classification accuracy are understudied problems. To establish the role of these factors, we consider an architecture of contrastive loss system such as SimCLR, where baseline model is replaced by geometrically invariant "hand-crafted" network ScatNet with small trainable adapter network and argue that the number of parameters of the whole system and the number of views can be considerably reduced while practically preserving the same classification accuracy. In addition, we investigate the impact of regularization strategies using pretext task learning based on an estimation of parameters of augmentation transform such as rotation and jigsaw permutation for both traditional baseline models and ScatNet based models. Finally, we demonstrate that the proposed architecture with pretext task learning regularization achieves the state-of-the-art classification performance with a smaller number of trainable parameters and with reduced number of views.

cs.CV↗

arXiv2015

Sparse Multi-layer Image Approximation: Facial Image Compression

We propose a scheme for multi-layer representation of images. The problem is first treated from an information-theoretic viewpoint where we analyze the behavior of different sources of information under a multi-layer data compression framework and compare it with a single-stage (shallow) structure. We then consider the image data as the source of information and link the proposed representation scheme to the problem of multi-layer dictionary learning for visual data. For the current work we focus on the problem of image compression for a special class of images where we report a considerable performance boost in terms of PSNR at high compression ratios in comparison with the JPEG2000 codec.

cs.CV↗

arXiv2011

On Multiple Hypothesis Testing with Rejection Option

We study the problem of multiple hypothesis testing (HT) in view of a rejection option. That model of HT has many different applications. Errors in testing of M hypotheses regarding the source distribution with an option of rejecting all those hypotheses are considered. The source is discrete and arbitrarily varying (AVS). The tradeoffs among error probability exponents/reliabilities associated with false acceptance of rejection decision and false rejection of true distribution are investigated and the optimal decision strategies are outlined. The main result is specialized for discrete memoryless sources (DMS) and studied further. An interesting insight that the analysis implies is the phenomenon (comprehensible in terms of supervised/unsupervised learning) that in optimal discrimination within M hypothetical distributions one permits always lower error than in deciding to decline the set of hypotheses. Geometric interpretations of the optimal decision schemes are given for the current and known bounds in multi-HT for AVS's.

cs.IT↗