<-- Icons -->
  • People
  • Research
  • Projects
  • Publications
  • Resources
ViCoS Lab

Vitjan Zavrtanik, PhD

  vitjan.zavrtanik@fri.uni-lj.si

Hi! I’m a final-year PhD candidate at the Visual Cognitive Systems Lab at the University of Ljubljana, Faculty of Computer and Information Science specializing in computer vision. My research is supervised by Prof. Danijel Skočaj, PhD and focuses on anomaly detection methods. I also collaborate closely with Prof. Matej Kristan, PhD and other colleagues on topics such as few-shot counting. I have previously worked as an intern at Amazon and CERN.

Research

My PhD research topic focuses on anomaly detection, however I am interested a broad range of topics.

Visual anomaly detection

This research focuses on the development of unsupervised visual anomaly detection methods. Trained on anomaly-free samples only, these methods attempt to remove the need for a difficult acquisition of a diverse set of anomalous objects while aiming to match the performance of supervised methods.

Low-shot counting

The main goal of this research is development of computer-vision-based automated counters that do not require large training datasets, but are adapted to a previously unseen category by using only a few training examples (few-shot), no training examples (zero-shot) or text-based prompts (text-prompt-based).

Dense object counting in underwater imagery

The main goal of this research is development of computer-vision-based automated counters applicable underwater imagery. Such counters are crucial for processing extremely large datasets, vastly reducing the required manual labor and facilitating census orders of magnitude grater than what is possible with standard techniques. The methods leverage learning on specific type of images to maximize a task-specific detection performance.

Publications

I am an author on articles published at top-tier conferences such as ICCV, ECCV, CVPR and NeurIPS.

My full bibliography can be seen in my Google Scholar.

Publication List:

  •  
    A Detect-and-Verify Paradigm for Low-Shot Counting - DAVE
    Jer Pelhan, Alan Lukežič, Vitjan Zavrtanik and Matej Kristan
    IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR), 2024
  •  
    A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
    Jer Pelhan, Alan Lukežič, Vitjan Zavrtanik and Matej Kristan
    The Thirty-Eighth Annual Conference on Neural Information Processing Systems, NeurIPS2024, 2024
  •  
    Anomalous Sound Detection by Feature-Level Anomaly Simulation
    Vitjan Zavrtanik, Matija Marolt, Matej Kristan and Danijel Skočaj
    ICASSP 2024, 2024
  •  
    Cheating Depth: Enhancing 3D Surface Anomaly Detection via Depth Simulation
    Vitjan Zavrtanik, Matej Kristan and Danijel Skočaj
    WACV 2024, 2024
  •  
    Keep DRÆMing: Discriminative 3D anomaly detection through anomaly simulation
    Vitjan Zavrtanik, Matej Kristan and Danijel Skočaj
    Pattern Recognition Letters, 2024
  •  
    TransFusion – A Transparency-Based Diffusion Model for Anomaly Detection
    Matic Fučka, Vitjan Zavrtanik and Danijel Skočaj
    ECCV 2024, 2024
  •  
    A Low-Shot Object Counting Network With Iterative Prototype Adaptation
    Nikola Djukic, Alan Lukežič, Vitjan Zavrtanik and Matej Kristan
    ICCV2023, 2023
  •  
    DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection
    Vitjan Zavrtanik, Matej Kristan and Danijel Skočaj
    ECCV 2022, 2022
  •  
    Analiza robustnosti globokih nenadzorovanih metod za detekcijo vizualnih anomalij
    Jakob Božič, Vitjan Zavrtanik and Danijel Skočaj
    ERK, 2021
  •  
    DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection
    Vitjan Zavrtanik, Matej Kristan and Danijel Skočaj
    ICCV 2021, 2021
  •  
    Reconstruction by inpainting for visual anomaly detection
    Vitjan Zavrtanik, Matej Kristan and Danijel Skočaj
    Pattern Recognition, Elsevier, 2021
  •  
    A segmentation-based approach for polyp counting in the wild
    Vitjan Zavrtanik, Martin Vodopivec and Matej Kristan
    Engineering Applications of Artificial Intelligence, Elsevier, 2020

Awards

  • 2023: Award for exceptional scientific achievement in the Republic of Slovenia in the year 2023 (ARIS).
  • 2022: Award for exceptional scientific achievement in the Republic of Slovenia in the year 2022 (ARIS).
  • 2021 Honorable mention of the research achievements of PhD students in 2020, awarded by FRI UNI-LJ (four awards given).
  • 2020 Award for outstanding research achievements of PhD students in 2020 (three awards given), awarded by The Faculty of computer and information science (FRI) UNI-LJ.

Service

Reviewer for CVPR, ECCV, ICCV, NeurIPS, ICLR, WACV, ICASSP.

Faculty of Computer and Information Science

Visual Cognitive Systems Laboratory

University of Ljubljana

Faculty of Computer and Information Science

Večna pot 113
SI-1000 Ljubljana
Slovenia
Tel.: +386 1 479 8245