Ivan Grubišić

Mr. Ivan Grubišić

University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, Zagreb, Grad, Croatia
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
IGIvan Grubišić
Ivan Grubišić
MOMarin Oršić
Marin Oršić
SŠSiniša Šegvić
Siniša Šegvić
Semi-supervised learning is an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires substantial effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp and photometric jittering. We experiment with efficient models due to their importance for real-time and low-power applications. Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations. Our perturbation model outperforms recent work and most of the contribution comes from the photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with coarse labels. Our source code is available at https://github.com/Ivan1248/semisup-seg-efficient.

30 January 2024 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
Petra BevandićPetra Bevandić
Petra Bevandić
MOMarin Oršić
Marin Oršić
JŠJosip Šarić
Josip Šarić
IGIvan Grubišić
Ivan Grubišić
SŠSiniša Šegvić
Siniša Šegvić

20 January 2023 in arXiv
Verified
Preprint
Open access
PDF file
IGIvan Grubišić
Ivan Grubišić
MOMarin Oršić
Marin Oršić
SŠSiniša Šegvić
Siniša Šegvić
Semi-supervised learning an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires significant effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp and photometric jittering. We experiment with efficient models due to their importance for real-time and low-power applications. Our experiments show clear advantages of (1) one-way consistency, (2) perturbing only the student branch, and (3) strong photometric and geometric perturbations. Our perturbation model outperforms recent work and most of the contribution comes from photometric component. Experiments with additional data from the large coarsely annotated subset of Cityscapes suggest that semi-supervised training can outperform supervised training with the coarse labels.

7 October 2021 in arXiv
Verified
Preprint
Open access
PDF file
Petra BevandićPetra Bevandić
Petra Bevandić
MOMarin Oršić
Marin Oršić
IGIvan Grubišić
Ivan Grubišić
JŠJosip Šarić
Josip Šarić
SŠSiniša Šegvić
Siniša Šegvić
We present our submission to the semantic segmentation contest of the Robust Vision Challenge held at ECCV 2020. The contest requires submitting the same model to seven benchmarks from three different domains. Our approach is based on the SwiftNet architecture with pyramidal fusion. We address inconsistent taxonomies with a single-level 193-dimensional softmax output. We strive to train with large batches in order to stabilize optimization of a hard recognition problem, and to favour smooth evolution of batchnorm statistics. We achieve this by implementing a custom backward step through log-sum-prob loss, and by using small crops before freezing the population statistics. Our model ranks first on the RVC semantic segmentation challenge as well as on the WildDash 2 leaderboard. This suggests that pyramidal fusion is competitive not only for efficient inference with lightweight backbones, but also in large-scale setups for multi-domain application.

12 March 2024 in arXiv
Verified
Preprint
Open access
PDF file
Petra BevandićPetra Bevandić
Petra Bevandić
MOMarin Oršić
Marin Oršić
IGIvan Grubišić
Ivan Grubišić
JŠJosip Šarić
Josip Šarić
SŠSiniša Šegvić
Siniša Šegvić
Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on multiple datasets becomes a method of choice towards strong generalization in usual scenes and graceful performance degradation in edge cases. Unfortunately, different datasets often have incompatible labels. For instance, the Cityscapes road class subsumes all driving surfaces, while Vistas defines separate classes for road markings, manholes etc. Furthermore, many datasets have overlapping labels. For instance, pickups are labeled as trucks in VIPER, cars in Vistas, and vans in ADE20k. We address this challenge by considering labels as unions of universal visual concepts. This allows seamless and principled learning on multi-domain dataset collections without requiring any relabeling effort. Our method achieves competitive within-dataset and cross-dataset generalization, as well as ability to learn visual concepts which are not separately labeled in any of the training datasets. Experiments reveal competitive or state-of-the-art performance on two multi-domain dataset collections and on the WildDash 2 benchmark.

2 September 2024 in arXiv
Verified
Preprint
Open access
PDF file
ISIvan Sabolić
Ivan Sabolić
IGIvan Grubišić
Ivan Grubišić
SŠSiniša Šegvić
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 data injects a backdoor which causes malicious inference in selected test samples. Most defenses mitigate such attacks through various modifications of the discriminative learning procedure. In contrast, this paper explores an approach based on generative modelling of per-class distributions in a self-supervised representation space. Interestingly, these representations get either preserved or heavily disturbed under recent backdoor attacks. In both cases, we find that per-class generative models allow to detect poisoned data and cleanse the dataset. Experiments show that training on cleansed dataset greatly reduces the attack success rate and retains the accuracy on benign inputs.