3 citations · 6 across the 10 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Backdoor Defense through Self-Supervised and Generative Learning
Ivan Sabolić, Ivan Grubišić, Siniša Šegvić
Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such…
cs.CV2024
MC-PanDA: Mask Confidence for Panoptic Domain Adaptation
Ivan Martinović, Josip Šarić, Siniša Šegvić
Domain adaptive panoptic segmentation promises to resolve the long tail of corner cases in natural scene understanding. Previous state of the art addresses this problem with cross-…
cs.CV2024★ 2 cited
Outlier detection by ensembling uncertainty with negative objectness
Anja Delić, Matej Grcić, Siniša Šegvić
Outlier detection is an essential capability in safety-critical applications of supervised visual recognition. Most of the existing methods deliver best results by encouraging stan…