About

I'm a PhD student working in the Visual Inference lab at TU Darmstadt in Germany. My research focuses on scene parsing in contexts of limited supervision. I obtained my Master's in Computer Science from University of Bonn (Germany). Earlier, I received a Diploma degree in Mechanical Engineering from Moscow Aviation Institute (specialising in Jet Engines), but since then, have turned to more down-to-earth matters.

Recent Projects

  • Self-supervised Augmentation Consistency for Adapting Semantic Segmentation

    Nikita Araslanov and Stefan Roth

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

  • Single-Stage Semantic Segmentation from Image Labels

    Nikita Araslanov and Stefan Roth

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

    Paper | Code

  • Markov Decision Process for Video Generation

    Vladyslav Yushchenko, Nikita Araslanov and Stefan Roth

    International Conference on Computer Vision (ICCV) Workshops, 2019

    Paper | Website

  • Actor-Critic Instance Segmentation

    Nikita Araslanov, Constantin A. Rothkopf and Stefan Roth

    Conference on Computer Vision and Pattern Recognition (CVPR), 2019

    Paper | Code

  • Efficient Single-view 3D Co-segmentation
    using Shape Similarity and Spatial Part Relations

    Nikita Araslanov, Seongyong Koo, Juergen Gall, and Sven Behnke

    38th German Conference on Pattern Recognition (GCPR), 2016

    Paper | Dataset

Google Scholar