Francesco Barbato | Post Doc

@inproceedings{rizzoli2025cars,

title = {When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather},

author = {Giulia Rizzoli and Matteo Caligiuri and Donald Shenaj and Francesco Barbato and Pietro Zanuttigh},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},

journal = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{barbato2023continualb,

title = {Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network},

author = {Francesco Barbato and Elena Camuffo and Simone Milani and Pietro Zanuttigh},

url = {https://arxiv.org/pdf/2308.04702.pdf},

year  = {2024},

date = {2024-06-25},

urldate = {2024-06-25},

booktitle = {IEEE International Conference on Image Processing (ICIP)},

journal = {arXiv preprint arXiv:2308.04702},

abstract = {State-of-the-art multimodal semantic segmentation approaches combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. Regrettably, this strong assumption may not hold in real-world scenarios, where sensors are prone to failure or can face adverse conditions (night-time, rain, fog, etc.) that make the acquired information unreliable. Moreover, these architectures tend to fail in continual learning scenarios. In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly-coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing. This makes our model reliable even in safetycritical settings, as is the case of autonomous driving. We evaluate our approach on the SemanticKITTI dataset, comparing it with our closest competitor. We also introduce an ad-hoc continual learning scheme and show results in a class-incremental continual learning scenario that prove the effectiveness of the approach also in this setting.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{10.1145/3625468.3647623,

title = {A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation},

author = {Francesco Barbato and Umberto Michieli and Mehmet Kerim Yucel and Pietro Zanuttigh and Mete Ozay},

url = {https://doi.org/10.1145/3625468.3647623},

doi = {10.1145/3625468.3647623},

isbn = {9798400704123},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

booktitle = {Proceedings of the 15th ACM Multimedia Systems Conference},

pages = {190–201},

publisher = {Association for Computing Machinery},

address = {, Bari, Italy,},

series = {MMSys '24},

abstract = {Performance degradation caused by corrupted multimedia samples is a critical challenge for machine learning models. Previously, three groups of approaches have been proposed to tackle this issue: i) enhancer and denoiser modules to improve the quality of the noisy data, ii) data augmentation approaches, and iii) domain adaptation strategies. All have drawbacks limiting applicability; the first requires paired clean-corrupted data for training and has an high computational cost, while the others can only be used on the same task they were trained on. In this paper, we propose SyMPIE to solve these shortcomings, designing a small, modular, and efficient system to enhance input data for robust downstream multimedia understanding with minimal computational cost. Our SyMPIE is pre-trained on an upstream task/network that should not match the downstream ones and does not need paired clean-corrupted samples. Our key insight is that most input corruptions found in real-world tasks can be modeled through global operations on color channels of images or spatial filters with small kernels. We validate our approach on multiple datasets and tasks, such as image classification (on ImageNetC, ImageNetC-Bar, VizWiz, and a newly proposed mixed corruption benchmark named ImageNetC-mixed) and semantic segmentation (on Cityscapes, ACDC, and DarkZurich) with consistent improvements of about 5% relative accuracy gain across the board1.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{barbato2023depthformer,

title = {DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks},

author = {Francesco Barbato and Giulia Rizzoli and Pietro Zanuttigh},

year  = {2023},

date = {2023-01-01},

booktitle = {ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{rizzoli2023syndrone,

title = {SynDrone-Multi-Modal UAV Dataset for Urban Scenarios},

author = {Giulia Rizzoli and Francesco Barbato and Matteo Caligiuri and Pietro Zanuttigh},

year  = {2023},

date = {2023-01-01},

urldate = {2023-01-01},

booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision},

pages = {2210–2220},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Barbato2021,

title = {Latent space regularization for unsupervised domain adaptation in semantic segmentation},

author = {Francesco Barbato and Marco Toldo and Umberto Michieli and Pietro Zanuttigh},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

pages = {2835--2845},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}