Zobrazeno 1 - 10
of 201
pro vyhledávání: '"Zanuttigh, Pietro"'
Current weakly-supervised incremental learning for semantic segmentation (WILSS) approaches only consider replacing pixel-level annotations with image-level labels, while the training images are still from well-designed datasets. In this work, we arg
Externí odkaz:
http://arxiv.org/abs/2407.13363
Recent years have seen object detection robotic systems deployed in several personal devices (e.g., home robots and appliances). This has highlighted a challenge in their design, i.e., they cannot efficiently update their knowledge to distinguish bet
Externí odkaz:
http://arxiv.org/abs/2407.01193
The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic. Recent works showed the feasibility of this idea exploiting transient imaging data produced by custom direct Time of F
Externí odkaz:
http://arxiv.org/abs/2403.19376
In Federated Learning (FL), multiple clients collaboratively train a global model without sharing private data. In semantic segmentation, the Federated source Free Domain Adaptation (FFreeDA) setting is of particular interest, where clients undergo u
Externí odkaz:
http://arxiv.org/abs/2403.13762
In multimedia understanding tasks, corrupted samples pose a critical challenge, because when fed to machine learning models they lead to performance degradation. In the past, three groups of approaches have been proposed to handle noisy data: i) enha
Externí odkaz:
http://arxiv.org/abs/2402.18402
Autor:
Martin-Turrero, Carmen, Bouvier, Maxence, Breitenstein, Manuel, Zanuttigh, Pietro, Parret, Vincent
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning (2024), in Proceedings of Machine Learning Research 235:48837-48854
We seek to enable classic processing of continuous ultra-sparse spatiotemporal data generated by event-based sensors with dense machine learning models. We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous processing th
Externí odkaz:
http://arxiv.org/abs/2402.01393
Autor:
Liu, Chang, Rizzoli, Giulia, Barbato, Francesco, Maracani, Andrea, Toldo, Marco, Michieli, Umberto, Niu, Yi, Zanuttigh, Pietro
Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed. In this p
Externí odkaz:
http://arxiv.org/abs/2309.10479
Neural implicit modeling permits to achieve impressive 3D reconstruction results on small objects, while it exhibits significant limitations in large indoor scenes. In this work, we propose a novel neural implicit modeling method that leverages multi
Externí odkaz:
http://arxiv.org/abs/2309.07021
The development of computer vision algorithms for Unmanned Aerial Vehicles (UAVs) imagery heavily relies on the availability of annotated high-resolution aerial data. However, the scarcity of large-scale real datasets with pixel-level annotations pos
Externí odkaz:
http://arxiv.org/abs/2308.10491
State-of-the-art multimodal semantic segmentation strategies combining LiDAR and color data are usually designed on top of asymmetric information-sharing schemes and assume that both modalities are always available. This strong assumption may not hol
Externí odkaz:
http://arxiv.org/abs/2308.04702