11 citations · 19 across the 10 of their papers we have counts for
11 papers
Uncertainty Estimation for 3D Object Detection via Evidential Learning
Nikita Durasov, Rafid Mahmood, Jiwoong Choi +4
3D object detection is an essential task for computer vision applications in autonomous vehicles and robotics. However, models often struggle to quantify detection reliability, lea…
IT: Idempotent Test-Time Training
Nikita Durasov, Assaf Shocher, Doruk Oner +3
Deep learning models often struggle when deployed in real-world settings due to distribution shifts between training and test data. While existing approaches like domain adaptation…
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models
Samar Fares, Klea Ziu, Toluwani Aremu +5
Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses. To…
Enabling Uncertainty Estimation in Iterative Neural Networks
Nikita Durasov, Doruk Oner, Jonathan Donier +2
Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that…
PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings
Nikita Durasov, Nik Dorndorf, Pascal Fua
Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning…
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
Nikita Durasov, Nik Dorndorf, Hieu Le +1
Whereas the ability of deep networks to produce useful predictions has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approa…
How to Boost Face Recognition with StyleGAN?
Artem Sevastopolsky, Yury Malkov, Nikita Durasov +2
State-of-the-art face recognition systems require vast amounts of labeled training data. Given the priority of privacy in face recognition applications, the data is limited to cele…
DEBOSH: Deep Bayesian Shape Optimization
Nikita Durasov, Artem Lukoyanov, Jonathan Donier +1
Graph Neural Networks (GNNs) can predict the performance of an industrial design quickly and accurately and be used to optimize its shape effectively. However, to fully explore the…
Leveraging Self-Supervision for Cross-Domain Crowd Counting
Weizhe Liu, Nikita Durasov, Pascal Fua
State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density. While effective, these data-driven approaches rely on large amount o…
Masksembles for Uncertainty Estimation
Nikita Durasov, Timur Bagautdinov, Pierre Baque +1
Deep neural networks have amply demonstrated their prowess but estimating the reliability of their predictions remains challenging. Deep Ensembles are widely considered as being on…
Double Refinement Network for Efficient Indoor Monocular Depth Estimation
Nikita Durasov, Mikhail Romanov, Valeriya Bubnova +2
Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image. It is an important problem in computer vision and is usually solved u…