Nazir Nayal

Docotoral Researcher @ Max Planck Institute for Informatics

personal/graduation_day.jpg

E1 4 - Room 624

Max-Planck-Institut für Informatik

Saarland Informatics Campus

Campus E1 4 66123 Saarbrücken, Germany

I am a doctoral researcher at Computer Vision and Machine Learning Department (D2) at the Max Planck Institute for Informatics in Saarbrücken, Germany, and a PhD student at Saarland University as part of the CS@Max Planck Doctoral Program.

I obtained my Computer Sciences and Engineering MSc degree from Koç University in Istanbul, Turkey, where I was a research fellow at the Koç University & İş Bankası Artificial Intelligence Center (KUIS AI), working under the supervision of Fatma Güney and João F. Henriques from VGG-Oxford.

I graduated with a BSc from Koç University Computer Engineering Department and was a recipient of Abdulla Al Ghurair Foundation for Education (AGFE) STEM Scholarship.

Research

My previous work was mainly on open-world segmentation and uncertainty estimation. Broadly interested in deep learning, computer vision, generative models, 3D Reconstruction, multi-modality, open-world learning, uncertainty.

news

Sep 15, 2024 Joined the Computer Vision and Machine Learning department at the Max Planck Institute for Informatics (MPI-INF) as a PhD student through the CS@Max Planck Doctoral Program.
Sep 10, 2024 Our new paper “A Likelihood Ratio-Based Approach to Segmenting Unknown Objects” is out!
Sep 24, 2023 Started as a Graduate Student Visitor at VGG Oxford.
Sep 04, 2023 Defended by MSc Thesis titled “RbA: Segmenting Unknown Regions Rejected by All using Mask Classifiers”
Jul 15, 2023 Our paper “ RbA: Segmenting Unknown Regions Rejected by All” was accepted at ICCV 2023!

latest posts

selected publications

  1. RbA: Segmenting Unknown Regions Rejected by All
    Nazir Nayal, Mısra Yavuz, João F. Henriques, and Fatma Güney
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023
  2. Arxiv
    UEM_preview.png
    A Likelihood Ratio-Based Approach to Segmenting Unknown Objects
    Nazir Nayal, Youssef Shoeb, and Fatma Güney
    arXiv preprint arXiv:2409.06424, 2024