activity
20172024
most citedInformation bottleneck through variational glasses

23 citations · 27 across the 11 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

Benchmarking 2D Egocentric Hand Pose Datasets

Olga Taran, Damian M. Manzone, Jose Zariffa

Hand pose estimation from egocentric video has broad implications across various domains, including human-computer interaction, assistive technologies, activity recognition, and ro…

cs.CV2022

Digital twins of physical printing-imaging channel

Yury Belousov, Brian Pulfer, Roman Chaban +4

In this paper, we address the problem of modeling a printing-imaging channel built on a machine learning approach a.k.a. digital twin for anti-counterfeiting applications based on…

cs.CV2022

Anomaly localization for copy detection patterns through print estimations

Brian Pulfer, Yury Belousov, Joakim Tutt +4

Copy detection patterns (CDP) are recent technologies for protecting products from counterfeiting. However, in contrast to traditional copy fakes, deep learning-based fakes have sh…

cs.CV2021

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

Vitaliy Kinakh, Olga Taran, Svyatoslav Voloshynovskiy

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…

cs.CV201923 cited

Information bottleneck through variational glasses

Slava Voloshynovskiy, Mouad Kondah, Shideh Rezaeifar +3

Information bottleneck (IB) principle [1] has become an important element in information-theoretic analysis of deep models. Many state-of-the-art generative models of both Variatio…

cs.CV2018

Classification by Re-generation: Towards Classification Based on Variational Inference

Shideh Rezaeifar, Olga Taran, Slava Voloshynovskiy

As Deep Neural Networks (DNNs) are considered the state-of-the-art in many classification tasks, the question of their semantic generalizations has been raised. To address semantic…