Josip Šarić

Ivan Sabolić, Marin Oršić, Josip Šarić et al.

Supervised fine-tuning is the predominant approach for adapting autoregressive vision-language models to downstream tasks. Recent work has shown that this paradigm is highly vulnerable to backdoor attacks, and that existing defenses are ineffective in open-ended generation settings. In response, we propose BYORn, a backdoor-robust fine-tuning framework motivated by the observation that poisoned target responses are often semantically implausible given the corresponding image-text inputs and a pretrained model. BYORn identifies such misaligned responses and dynamically replaces them with alternative responses generated by the model, thereby breaking the correlation between triggers and target outputs. The resulting objective gradient corresponds to the gradient of the empirical estimate of the population risk upper bound over the clean data distribution. Empirically, BYORn consistently improves robustness to backdoor attacks while preserving clean-task performance, establishing a new trade-off frontier between generalization and attack success rate. Finally, we demonstrate that BYORn remains effective against adaptive attacks specifically designed to circumvent the proposed defense.

Benjamin Kiefer, Jan Lukas Augustin, Jon Muhovič et al.

The 4th Workshop on Maritime Computer Vision (MaCVi) is organized as part of CVPR 2026. This edition features five benchmark challenges with emphasis on both predictive accuracy and embedded real-time feasibility. This report summarizes the MaCVi 2026 challenge setup, evaluation protocols, datasets, and benchmark tracks, and presents quantitative results, qualitative comparisons, and cross-challenge analyses of emerging method trends. We also include technical reports from top-performing teams to highlight practical design choices and lessons learned across the benchmark suite. Datasets, leaderboards, and challenge resources are available at https://macvi.org/workshop/cvpr26.

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-task consistency, careful system-level optimization and heuristic improvement of teacher predictions. In contrast, we propose to build upon remarkable capability of mask transformers to estimate their own prediction uncertainty. Our method avoids noise amplification by leveraging fine-grained confidence of panoptic teacher predictions. In particular, we modulate the loss with mask-wide confidence and discourage back-propagation in pixels with uncertain teacher or confident student. Experimental evaluation on standard benchmarks reveals a substantial contribution of the proposed selection techniques. We report 47.4 PQ on Synthia to Cityscapes, which corresponds to an improvement of 6.2 percentage points over the state of the art. The source code is available at https://github.com/helen1c/MC-PanDA.

Josip Šarić, Marin Oršić, Siniša Šegvić

Dense panoptic prediction is a key ingredient in many existing applications such as autonomous driving, automated warehouses or remote sensing. Many of these applications require fast inference over large input resolutions on affordable or even embedded hardware. We propose to achieve this goal by trading off backbone capacity for multi-scale feature extraction. In comparison with contemporaneous approaches to panoptic segmentation, the main novelties of our method are efficient scale-equivariant feature extraction, cross-scale upsampling through pyramidal fusion and boundary-aware learning of pixel-to-instance assignment. The proposed method is very well suited for remote sensing imagery due to the huge number of pixels in typical city-wide and region-wide datasets. We present panoptic experiments on Cityscapes, Vistas, COCO and the BSB-Aerial dataset. Our models outperform the state of the art on the BSB-Aerial dataset while being able to process more than a hundred 1MPx images per second on a RTX3090 GPU with FP16 precision and TensorRT optimization.

Petra Bevandić, Marin Oršić, Ivan Grubišić et al.

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.

Matej Grcić, Josip Šarić, Siniša Šegvić

Most dense recognition approaches bring a separate decision in each particular pixel. These approaches deliver competitive performance in usual closed-set setups. However, important applications in the wild typically require strong performance in presence of outliers. We show that this demanding setup greatly benefit from mask-level predictions, even in the case of non-finetuned baseline models. Moreover, we propose an alternative formulation of dense recognition uncertainty that effectively reduces false positive responses at semantic borders. The proposed formulation produces a further improvement over a very strong baseline and sets the new state of the art in outlier-aware semantic segmentation with and without training on negative data. Our contributions also lead to performance improvement in a recent panoptic setup. In-depth experiments confirm that our approach succeeds due to implicit aggregation of pixel-level cues into mask-level predictions.

Ivan Martinović, Josip Šarić, Marin Oršić et al.

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 corpus of unlabeled images. Although foundation models could further account for label scarcity, effective mechanisms for their exploitation remain underexplored. We address this by devising a novel semi-supervised panoptic approach fueled by two dedicated foundation models. We enhance recognition by complementing unsupervised mask-transformer consistency with zero-shot classification of CLIP features. We enhance localization by class-agnostic decoder warm-up with respect to SAM pseudo-labels. The resulting decoupled enhancement of recognition and localization (DEARLi) particularly excels in the most challenging semi-supervised scenarios with large taxonomies and limited labeled data. Moreover, DEARLi outperforms the state of the art in semi-supervised semantic segmentation by a large margin while requiring 8x less GPU memory, in spite of being trained only for the panoptic objective. We observe 29.9 PQ and 38.9 mIoU on ADE20K with only 158 labeled images. The source code is available at https://github.com/helen1c/DEARLi.

Benjamin Kiefer, Lojze Žust, Jon Muhovič et al.

The 3rd Workshop on Maritime Computer Vision (MaCVi) 2025 addresses maritime computer vision for Unmanned Surface Vehicles (USV) and underwater. This report offers a comprehensive overview of the findings from the challenges. We provide both statistical and qualitative analyses, evaluating trends from over 700 submissions. All datasets, evaluation code, and the leaderboard are available to the public at https://macvi.org/workshop/macvi25.

Josip Šarić, Ivan Martinović, Matej Kristan et al.

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 language-image pretraining on billions of image-caption pairs. Unfortunately, we observe that the promise is not delivered due to several bottlenecks that have caused the performance to plateau for almost two years. This paper proposes novel oracle components that identify and decouple these bottlenecks by taking advantage of the groundtruth information. The presented validation experiments deliver important empirical findings that provide a deeper insight into the failures of open-vocabulary models and suggest prominent approaches to unlock the future research.

Petra Bevandić, Marin Oršić, Ivan Grubišić et al.

Deep supervised models have an unprecedented capacity to absorb large quantities of training data. Hence, training on many datasets becomes a method of choice towards graceful degradation in unusual scenes. Unfortunately, different datasets often use incompatible labels. For instance, the Cityscapes road class subsumes all driving surfaces, while Vistas defines separate classes for road markings, manholes etc. We address this challenge by proposing a principled method for seamless learning on datasets with overlapping classes based on partial labels and probabilistic loss. 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.

Josip Šarić, Sacha Vražić, Siniša Šegvić

Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach consists of two modules. Feature-to-motion (F2M) module forecasts a dense deformation field that warps past features into their future positions. Feature-to-feature (F2F) module regresses the future features directly and is therefore able to account for emergent scenery. The compound F2MF model decouples the effects of motion from the effects of novelty in a task-agnostic manner. We aim to apply F2MF forecasting to the most subsampled and the most abstract representation of a desired single-frame model. Our design takes advantage of deformable convolutions and spatial correlation coefficients across neighbouring time instants. We perform experiments on three dense prediction tasks: semantic segmentation, instance-level segmentation, and panoptic segmentation. The results reveal state-of-the-art forecasting accuracy across three dense prediction tasks.

Kristijan Fugošić, Josip Šarić, Siniša Šegvić

This paper considers semantic forecasting in road-driving scenes. Most existing approaches address this problem as deterministic regression of future features or future predictions given observed frames. However, such approaches ignore the fact that future can not always be guessed with certainty. For example, when a car is about to turn around a corner, the road which is currently occluded by buildings may turn out to be either free to drive, or occupied by people, other vehicles or roadworks. When a deterministic model confronts such situation, its best guess is to forecast the most likely outcome. However, this is not acceptable since it defeats the purpose of forecasting to improve security. It also throws away valuable training data, since a deterministic model is unable to learn any deviation from the norm. We address this problem by providing more freedom to the model through allowing it to forecast different futures. We propose to formulate multimodal forecasting as sampling of a multimodal generative model conditioned on the observed frames. Experiments on the Cityscapes dataset reveal that our multimodal model outperforms its deterministic counterpart in short-term forecasting while performing slightly worse in the mid-term case.

Petra Bevandić, Marin Oršić, Ivan Grubišić et al.

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.

Josip Šarić, Marin Oršić, Tonći Antunović et al.

Future anticipation is of vital importance in autonomous driving and other decision-making systems. We present a method to anticipate semantic segmentation of future frames in driving scenarios based on feature-to-feature forecasting. Our method is based on a semantic segmentation model without lateral connections within the upsampling path. Such design ensures that the forecasting addresses only the most abstract features on a very coarse resolution. We further propose to express feature-to-feature forecasting with deformable convolutions. This increases the modelling power due to being able to represent different motion patterns within a single feature map. Experiments show that our models with deformable convolutions outperform their regular and dilated counterparts while minimally increasing the number of parameters. Our method achieves state of the art performance on the Cityscapes validation set when forecasting nine timesteps into the future.