profile photo

Hello!

I’m Nikita Durasov, a PhD student at EPFL IC (🇨🇭) where I work under the supervision of Professor Pascal Fua at the Computer Vision Laboratory on problems related to Deep Learning (🤖) and Computer Vision (👁).

Previously, I was a research scientist at NVIDIA, Apple, Amazon, and Samsung AI, working on problems related to Computer Vision and Deep Learning. I completed my bachelor's degree at MIPT (🇷🇺) in Applied Physics and Mathematics while also studying at the Yandex School of Data Analysis.


Research


I'm broadly interested in enhancing the interpretability and robustness of modern deep learning models through uncertainty quantification and bayesian methods.

Consequently, I'm also curious about new approaches to active learning, bayesian optimization, and other data-efficient techniques for various domains.

Mostly, my research is focused on computer vision and image processing tasks, but it is not limited to them. Occasionally, I delve into natural language processing and reinforcement learning.

I have also contributed as a reviewer for various academic conferences and journals, such as: CVPR NeurIPS ICLR ICML ICCV ECCV ICRA IROS ACCV RA-L IJCV AISTATS TPAMI TMLR, and other (full list).

My Stats from Google Scholar:

  • Citations: 198
  • h-index: 6
  • i10-index: 6

Publications

depth estimation photo
Enabling Uncertainty Estimation in Iterative Neural Networks

Nikita Durasov, Doruk Oner, Jonathan Donier, Hieu Le, Pascal Fua

ICML 2024

pdf | code | media | video | page

depth estimation photo
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Nikita Durasov, Nik Dorndorf, Hieu Le, Pascal Fua

TMLR 2024 ICMLW 2024

openreview | pdf | code | page

depth estimation photo
How to Boost Face Recognition with StyleGAN?

Artem Sevastopolsky, Yuri Malkov, Nikita Durasov, Luisa Verdoliva, Matthias Nießner

ICCV 2023

pdf | code | video | page

depth estimation photo
Leveraging Self-Supervision for Cross-Domain Crowd Counting

Weizhe Liu, Nikita Durasov, Pascal Fua

CVPR 2022 (Oral)

pdf | code | video | page

depth estimation photo
Masksembles for Uncertainty Estimation

Nikita Durasov, Timur Bagautdinov, Pierre Baque, Pascal Fua

CVPR 2021

pdf | code | media | video | page

depth estimation photo
Double refinement network for efficient indoor monocular depth estimation

Nikita Durasov, Mikhail Romanov, Valeriya Bubnova, Pavel Bogomolov, Anton Konushin

IROS 2019

pdf | video

depth estimation photo
Learning node embeddings for influence set completion

Sergei Ivanov, Nikita Durasov, Evgeny Burnaev

ICDM 2018

pdf | code

Preprints

depth estimation photo
MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

Samar Fares, Klea Ziu, Toluwani Aremu, Nikita Durasov, Martin Takáč, Pascal Fua, Karthik Nandakumar, Ivan Laptev

ARXIV 2024

pdf | page

depth estimation photo
PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings

Nikita Durasov, Nik Dorndorf, Pascal Fua

ARXIV 2022

pdf

depth estimation photo
DEBOSH: Deep Bayesian Shape Optimization

Nikita Durasov, Artem Lukoyanov, Jonathan Donier, Pascal Fua

ARXIV 2021

pdf | media | page

Invited Talks


  • 15/08/2024: "Deep Uncertainty" was presented at Mila - Quebec AI Institute in Montréal, Canada.
  • 10/04/2024: "Deep Uncertainty" was presented at UiT The Arctic University of Norway in Tromsø, Norway.
  • 12/02/2024: "Deep Uncertainty" was presented at MBZUAI in Abu Dhabi, UAE.
  • 08/01/2024: "Low-cost Uncertainty Estimation for Deep Learning" at CVLAB Group Meeting in Lausanne, Switzerland.
  • 02/10/2023: "Deep Uncertainty" was presented at Nordic AI Conference in Copenhagen, Sweden.
  • 17/08/2023: "Deep Uncertainty" was presented at Stony Brook University in New York, USA.
  • 16/08/2023: "Deep Uncertainty" was presented at NYU Courant Institute in New York, USA.
  • 09/08/2023: "Deep Uncertainty" was presented at Apple's Park in Cupertino, USA.
  • 08/08/2023: "Deep Uncertainty" was presented at Meta in San Francisco, USA.
  • 13/12/2022: "Masksembles for Uncertainty Estimation" at Uncertainty Reading Group at ETH in Zurich, Switzerland. [video]
  • 30/09/2022: "Enhanced Robustness of Transformer Detectors for Handling Omissions in Ground Truth Data" at Apple Development Center in Zurich, Switzerland.
  • 26/08/2022: "Single-shot Uncertainty Estimation" at CVLAB Group Meeting in Lausanne, Switzerland.
  • 26/04/2022: "Partial Active Learning with Incomplete Annotations" at VILAB Group Meeting in Lausanne, Switzerland.
  • 20/12/2021: "Robust Prediction of Stereo Disparity Under Uncertainty" at Amazon Prime Air in Graz, Austria.
  • 22/06/2021: "Masksembles for Uncertainty Estimation" at CVPR 2021. [video] [paper]