Matic Fučka

Researcher

About

I am a PhD student at the Visual Cognitive Systems Lab at the University of Ljubljana, Faculty of Computer and Information Science. My research is supervised by prof. dr. Danijel Skočaj and focuses on the development of methods for detecting anomalies.

I have a diverse range of research interest, such as visual anomaly detection, image generation, zero-shot semantic segmentation, few-shot learning, and the broader domains of computer vision and deep learning.

I am engaged in both research and industry projects, where I apply computer vision and deep learning techniques to address real-world problems, applications, and diverse challenges.

Research

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.

Projects

MUXAD - Multimodal Image Understanding for Explainable Anomaly Detection

January 2025 - December 2027
The functional objective of the project is to advance anomaly detection in images by developing multimodal models that integrate visual and linguistic information to not only detect if and where anomalies occur but also explain why. The main research goal is to create novel methods for semantic image understanding, zero-shot multimodal anomaly detection, and multimodal explanations that improve AI’s interpretability and transparency while reducing reliance on annotated data.

Awards

Teaching

I am actively involved in teaching at the University of Ljubljana, Faculty of Computer and Information Science as a teaching assistant at:

  • Deep Learning (Globoko Učenje) – Ongoing

Service

Reviewer for CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML, WACV and IJCV.

Publications

First author of papers published at CVPR, ECCV and ICCV. My full bibliography can be seen in my Google Scholar.