Zobrazeno 1 - 10
of 124
pro vyhledávání: '"Tommasi, Tatiana"'
Autor:
Rabino, Paolo, Tommasi, Tatiana
Interacting with real-world cluttered scenes pose several challenges to robotic agents that need to understand complex spatial dependencies among the observed objects to determine optimal pick sequences or efficient object retrieval strategies. Exist
Externí odkaz:
http://arxiv.org/abs/2409.02035
Autor:
Iurada, Leonardo, Cavagnero, Niccolò, Santos, Fernando Fernandes Dos, Averta, Giuseppe, Rech, Paolo, Tommasi, Tatiana
Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults. We address the latter by examining fault-tolerance in semantic segmentation models. Using establis
Externí odkaz:
http://arxiv.org/abs/2408.16952
Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training. We focus on this framework and propose a new pruning at initialization algorithm tha
Externí odkaz:
http://arxiv.org/abs/2406.01820
In the domain of computer vision, semantic segmentation emerges as a fundamental application within machine learning, wherein individual pixels of an image are classified into distinct semantic categories. This task transcends traditional accuracy me
Externí odkaz:
http://arxiv.org/abs/2403.19826
We introduce PolyDiff, the first diffusion-based approach capable of directly generating realistic and diverse 3D polygonal meshes. In contrast to methods that use alternate 3D shape representations (e.g. implicit representations), our approach is a
Externí odkaz:
http://arxiv.org/abs/2312.11417
Autor:
Tiboni, Gabriele, Klink, Pascal, Peters, Jan, Tommasi, Tatiana, D'Eramo, Carlo, Chalvatzaki, Georgia
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hinges on the choice of the sampling distribution of the dynamics parame
Externí odkaz:
http://arxiv.org/abs/2311.01885
Moving deep learning models from the laboratory setting to the open world entails preparing them to handle unforeseen conditions. In several applications the occurrence of novel classes during deployment poses a significant threat, thus it is crucial
Externí odkaz:
http://arxiv.org/abs/2310.03388
Autor:
Plizzari, Chiara, Goletto, Gabriele, Furnari, Antonino, Bansal, Siddhant, Ragusa, Francesco, Farinella, Giovanni Maria, Damen, Dima, Tommasi, Tatiana
What will the future be? We wonder! In this survey, we explore the gap between current research in egocentric vision and the ever-anticipated future, where wearable computing, with outward facing cameras and digital overlays, is expected to be integr
Externí odkaz:
http://arxiv.org/abs/2308.07123
Standard recognition approaches are unable to deal with novel categories at test time. Their overconfidence on the known classes makes the predictions unreliable for safety-critical applications such as healthcare or autonomous driving. Out-Of-Distri
Externí odkaz:
http://arxiv.org/abs/2307.06179
Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life. Although being of great support when making complex decisions, they might capture spurious data correlations an
Externí odkaz:
http://arxiv.org/abs/2303.14411