I'm a postdoc in the Computer Vision Group at TU Munich in Germany. My research focuses on visual scene understanding with limited supervision. Previously, I was a PhD student working at the Visual Inference Lab in TU Darmstadt. I obtained my Master's in Computer Science from University of Bonn. I also hold a Diploma degree in Mechanical Engineering from Moscow Aviation Institute (specialising in jets).


  • 14/09/2022 I successfully defended my PhD thesis "Deep Visual Parsing with Limited Supervision" (summa cum laude).
  • 21/05/2022 Happy to be among outstanding reviewers at CVPR '22.
  • 29/10/2021 I will be joining Daniel Cremers' group at TUM as a postdoc starting January 2022.
  • 28/09/2021 Our paper on unsupervised learning for video object segmentation has been accepted at NeurIPS '21.



Geometric Scene Understanding (Practical Course, 3SWS)

Course page


Computer Vision 3: Segmentation, Detection and Tracking (Lecture, 4SWS)

Details   |   Course page (TUM students only)


Semantic Self-adaptation:
Enhancing Generalization with a Single Sample

Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers and Stefan Roth

European Conference on Computer Vision (ECCV) Workshops, 2022

Workshop paper (short) | arXiv (preprint, long) | Code

Dense Unsupervised Learning for Video Segmentation

Nikita Araslanov, Simone Schaub-Meyer and Stefan Roth

Advances in Neural Information Processing Systems (NeurIPS), 2021

Paper | Supplemental | Code

Self-supervised Augmentation Consistency for Adapting Semantic Segmentation

Nikita Araslanov and Stefan Roth

Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Paper | Supplemental | Code

Single-Stage Semantic Segmentation from Image Labels

Nikita Araslanov and Stefan Roth

Conference on Computer Vision and Pattern Recognition (CVPR), 2020

Paper | Supplemental | Code

Google Scholar