Selected publications

Fine-grained Classes and How to Find Them

Matej Grcić, Artyom Gadetsky, Maria Brbić
International Conference on Machine Learning 2024
Paper: ArXiv Code: mlbio-epfl/falcon

Hybrid Open-set Segmentation with Synthetic Negative Data

Matej Grcić, Siniša Šegvić
IEEE Transactions on Pattern Analysis and Machine Intelligence 2024
Paper: ArXiv Code: matejgrcic/DenseHybrid

On Advantages of Mask-level Recognition for Outlier-aware Segmentation

Matej Grcić, Josip Šarić, Siniša Šegvić
CVPR2023 workshop Visual Anomaly and Novelty Detection (VAND 2023)
Paper: ArXiv Code: matejgrcic/Open-set-M2F

DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition

Matej Grcić, Petra Bevandić, Siniša Šegvić
European Conference on Computer Vision ECCV2022
Paper: ArXiv Code: matejgrcic/DenseHybrid

Densely connected normalizing flows

Matej Grcić, Ivan Grubišić, Siniša Šegvić
Neural Information Processing Systems 2021
Paper: ArXiv Code: matejgrcic/DenseFlow