activity
20192022
most citedUnsupervised Domain Adaptation in Semantic Segmentation: a Review

28 citations · 63 across the 10 of their papers we have counts for

collaborators

15 papers

cs.CV20223 cited

Learning with Style: Continual Semantic Segmentation Across Tasks and Domains

Marco Toldo, Umberto Michieli, Pietro Zanuttigh

Deep learning models dealing with image understanding in real-world settings must be able to adapt to a wide variety of tasks across different domains. Domain adaptation and class…

cs.CV20223 cited

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

Donald Shenaj, Eros Fanì, Marco Toldo +6

Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the co…

cs.CV20221 cited

SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints

Paolo Testolina, Francesco Barbato, Umberto Michieli +3

Accurate scene understanding from multiple sensors mounted on cars is a key requirement for autonomous driving systems. Nowadays, this task is mainly performed through data-hungry…

cs.CV2021

RECALL: Replay-based Continual Learning in Semantic Segmentation

Andrea Maracani, Umberto Michieli, Marco Toldo +1

Deep networks allow to obtain outstanding results in semantic segmentation, however they need to be trained in a single shot with a large amount of data. Continual learning setting…

cs.CV20213 cited

Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations

Francesco Barbato, Umberto Michieli, Marco Toldo +1

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do…

cs.LG202125 cited

Prototype Guided Federated Learning of Visual Feature Representations

Umberto Michieli, Mete Ozay

Federated Learning (FL) is a framework which enables distributed model training using a large corpus of decentralized training data. Existing methods aggregate models disregarding…