Zobrazeno 1 - 10
of 119
pro vyhledávání: '"Kinakh SO"'
In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an information-theor
Externí odkaz:
http://arxiv.org/abs/2410.02069
Autor:
Kinakh, Vitaliy, Pulfer, Brian, Belousov, Yury, Fernandez, Pierre, Furon, Teddy, Voloshynovskiy, Slava
The vast amounts of digital content captured from the real world or AI-generated media necessitate methods for copyright protection, traceability, or data provenance verification. Digital watermarking serves as a crucial approach to address these cha
Externí odkaz:
http://arxiv.org/abs/2409.18211
Autor:
Kinakh, Vitaliy, Voloshynovskiy, Slava
Generating synthetic tabular data is critical in machine learning, especially when real data is limited or sensitive. Traditional generative models often face challenges due to the unique characteristics of tabular data, such as mixed data types and
Externí odkaz:
http://arxiv.org/abs/2409.13882
Vision foundation models, which have demonstrated significant potential in multimedia applications, are often underutilized in the natural sciences. This is primarily due to mismatches between the nature of domain-specific scientific data and the typ
Externí odkaz:
http://arxiv.org/abs/2409.11175
Autor:
Lastufka, Erica, Bait, Omkar, Taran, Olga, Drozdova, Mariia, Kinakh, Vitaliy, Piras, Davide, Audard, Marc, Dessauges-Zavadsky, Miroslava, Holotyak, Taras, Schaerer, Daniel, Voloshynovskiy, Svyatoslav
Publikováno v:
A&A 690, A310 (2024)
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
Externí odkaz:
http://arxiv.org/abs/2408.06147
Autor:
Ramunno, Francesco P., Hackstein, S., Kinakh, V., Drozdova, M., Quetant, G., Csillaghy, A., Voloshynovskiy, S.
Given the rarity of significant solar flares compared to smaller ones, training effective machine learning models for solar activity forecasting is challenging due to insufficient data. This study proposes using generative deep learning models, speci
Externí odkaz:
http://arxiv.org/abs/2404.02552
Autor:
Drozdova, Mariia, Kinakh, Vitaliy, Bait, Omkar, Taran, Olga, Lastufka, Erica, Dessauges-Zavadsky, Miroslava, Holotyak, Taras, Schaerer, Daniel, Voloshynovskiy, Slava
Reconstructing sky models from dirty radio images for accurate source localization and flux estimation is crucial for studying galaxy evolution at high redshift, especially in deep fields using instruments like the Atacama Large Millimetre Array (ALM
Externí odkaz:
http://arxiv.org/abs/2402.10204
Publikováno v:
Qu\'etant, G.; Belousov, Y.; Kinakh, V.; Voloshynovskiy, S. TURBO: The Swiss Knife of Auto-Encoders. Entropy 2023, 25, 1471
We present a novel information-theoretic framework, termed as TURBO, designed to systematically analyse and generalise auto-encoding methods. We start by examining the principles of information bottleneck and bottleneck-based networks in the auto-enc
Externí odkaz:
http://arxiv.org/abs/2311.06527
Copy detection patterns (CDP) present an efficient technique for product protection against counterfeiting. However, the complexity of studying CDP production variability often results in time-consuming and costly procedures, limiting CDP scalability
Externí odkaz:
http://arxiv.org/abs/2309.16866
MV-MR: multi-views and multi-representations for self-supervised learning and knowledge distillation
Publikováno v:
Entropy. 2024; 26(6):466
We present a new method of self-supervised learning and knowledge distillation based on the multi-views and multi-representations (MV-MR). The MV-MR is based on the maximization of dependence between learnable embeddings from augmented and non-augmen
Externí odkaz:
http://arxiv.org/abs/2303.12130