activity
20192023
most citedPost-Train Adaptive U-Net for Image Segmentation

2 citations · 4 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2023★ 2 cited

Post-Train Adaptive U-Net for Image Segmentation

Kostiantyn Khabarlak

Typical neural network architectures used for image segmentation cannot be changed without further training. This is quite limiting as the network might not only be executed on a p…

cs.CV2022

Post-Train Adaptive MobileNet for Fast Anti-Spoofing

Kostiantyn Khabarlak

Many applications require high accuracy of neural networks as well as low latency and user data privacy guaranty. Face anti-spoofing is one of such tasks. However, a single model m…

cs.CV2022★ 1 cited

Face Detection on Mobile: Five Implementations and Analysis

Kostiantyn Khabarlak

In many practical cases face detection on smartphones or other highly portable devices is a necessity. Applications include mobile face access control systems, driver status tracki…

cs.LG2021

Simultaneous Perturbation Method for Multi-Task Weight Optimization in One-Shot Meta-Learning

Andrei Boiarov, Kostiantyn Khabarlak, Igor Yastrebov

Meta-learning methods aim to build learning algorithms capable of quickly adapting to new tasks in low-data regime. One of the most difficult benchmarks of such algorithms is a one…

cs.CR2021

Mobile Access Control System Based on RFID Tags And Facial Information

Kostiantyn Khabarlak, Larysa Koriashkina

Better access control system security comes at a higher price. It many cases the price is too high for small companies, leaving them vulnerable with cheap and insecure systems. In…

cs.CV2021

Fast Facial Landmark Detection and Applications: A Survey

Kostiantyn Khabarlak, Larysa Koriashkina

Dense facial landmark detection is one of the key elements of face processing pipeline. It is used in virtual face reenactment, emotion recognition, driver status tracking, etc. Ea…