3 citations · 6 across the 10 of their papers we have counts for
12 papers
MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic Segmentation
Ivan Martinović, Josip Šarić, Yuki M. Asano +1
Unsupervised domain adaptation (UDA) reduces the annotation burden in panoptic segmentation by leveraging a cost-effectively labeled source domain (e.g., synthetic) and an unlabele…
SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation
Naomi Kombol, Ivan Martinović, Siniša Šegvić +1
Foundational Vision Transformers (ViTs) have limited effectiveness in tasks requiring fine-grained spatial understanding, due to their fixed pre-training resolution and inherently…
What Holds Back Open-Vocabulary Segmentation?
Josip Šarić, Ivan Martinović, Matej Kristan +1
Standard segmentation setups are unable to deliver models that can recognize concepts outside the training taxonomy. Open-vocabulary approaches promise to close this gap through la…
DEARLi: Decoupled Enhancement of Recognition and Localization for Semi-supervised Panoptic Segmentation
Ivan Martinović, Josip Šarić, Marin Oršić +2
Pixel-level annotation is expensive and time-consuming. Semi-supervised segmentation methods address this challenge by learning models on few labeled images alongside a large corpu…
Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection
Anja Delić, Matej Grcić, Siniša Šegvić
Detecting anomalous human behaviour is an important visual task in safety-critical applications such as healthcare monitoring, workplace safety, or public surveillance. In these co…
A Survey on Training-free Open-Vocabulary Semantic Segmentation
Naomi Kombol, Ivan Martinović, Siniša Šegvić
Semantic segmentation is one of the most fundamental tasks in image understanding with a long history of research, and subsequently a myriad of different approaches. Traditional me…
Seal Your Backdoor with Variational Defense
Ivan Sabolić, Matej Grcić, Siniša Šegvić
We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted la…
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…
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-…
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…
Quantile-based Maximum Likelihood Training for Outlier Detection
Masoud Taghikhah, Nishant Kumar, Siniša Šegvić +2
Discriminative learning effectively predicts true object class for image classification. However, it often results in false positives for outliers, posing critical concerns in appl…
Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification
Marin Kačan, Marko Ševrović, Siniša Šegvić
Road-safety inspection is an indispensable instrument for reducing road-accident fatalities contributed to road infrastructure. Recent work formalizes road-safety assessment in ter…