default search action
Umberto Michieli
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
- [j9]Marco Toldo
, Umberto Michieli
Learning With Style: Continual Semantic Segmentation Across Tasks and Domains. IEEE Trans. Pattern Anal. Mach. Intell. 46(11): 7434-7450 (2024) - [j8]Francesco Barbato
Road scenes segmentation across different domains by disentangling latent representations. Vis. Comput. 40(2): 811-830 (2024) - [c24]Umberto Michieli
HOP to the Next Tasks and Domains for Continual Learning in NLP. AAAI 2024: 14359-14369 - [c23]Hasan Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi, Bernard Ghanem, Mete Ozay:
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. EMNLP (Findings) 2024: 13033-13046 - [c22]Elena Camuffo, Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay:
FFT-Based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. ICASSP 2024: 2795-2799 - [c21]Hafiz Tiomoko Ali, Umberto Michieli, Ji Joong Moon, Daehyun Kim, Mete Ozay:
Deep Neural Network Models Trained with a Fixed Random Classifier Transfer Better Across Domains. ICASSP 2024: 5305-5309 - [c20]Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay:
Object-Conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. ICASSP 2024: 7885-7889 - [c19]Francesco Barbato
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. MMSys 2024: 190-201 - [i34]Francesco Barbato, Umberto Michieli
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation. CoRR abs/2402.18402 (2024) - [i33]Umberto Michieli
HOP to the Next Tasks and Domains for Continual Learning in NLP. CoRR abs/2402.18449 (2024) - [i32]Hafiz Tiomoko Ali, Umberto Michieli
Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains. CoRR abs/2402.18614 (2024) - [i31]Elena Camuffo, Umberto Michieli
FFT-based Selection and Optimization of Statistics for Robust Recognition of Severely Corrupted Images. CoRR abs/2403.14335 (2024) - [i30]Umberto Michieli, Jijoong Moon, Daehyun Kim, Mete Ozay:
Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition. CoRR abs/2404.01397 (2024) - [i29]Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati, Philip Torr, Adel Bibi
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch. CoRR abs/2406.14563 (2024) - [i28]Francesco Barbato, Umberto Michieli, Jijoong Moon, Pietro Zanuttigh, Mete Ozay:
Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection. CoRR abs/2407.01193 (2024) - [i27]Elena Camuffo, Umberto Michieli, Simone Milani, Jijoong Moon, Mete Ozay:
Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statistics. CoRR abs/2407.06450 (2024) - [i26]Kirill Paramonov, Jia-Xing Zhong, Umberto Michieli, Jijoong Moon, Mete Ozay:
Swiss DINO: Efficient and Versatile Vision Framework for On-device Personal Object Search. CoRR abs/2407.07541 (2024) - [i25]Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud, Taha Ceritli, Hayder Elesedy, Mete Ozay, Peter Richtárik:
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation. CoRR abs/2410.08305 (2024) - 2023
- [j7]Umberto Michieli
Federated Learning via Attentive Margin of Semantic Feature Representations. IEEE Internet Things J. 10(2): 1517-1535 (2023) - [j6]Paolo Testolina
SELMA: SEmantic Large-Scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints. IEEE Trans. Intell. Transp. Syst. 24(7): 7012-7024 (2023) - [c18]James Stewart, Umberto Michieli
Data-Free Model Pruning at Initialization via Expanders. CVPR Workshops 2023: 4519-4524 - [c17]D. Campagnolo, Elena Camuffo, Umberto Michieli
Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation. ICIP 2023: 291-295 - [c16]Umberto Michieli
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. INTERSPEECH 2023: 1628-1632 - [c15]Edward Fish, Umberto Michieli
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. INTERSPEECH 2023: 3232-3236 - [c14]Umberto Michieli
Online Continual Learning for Robust Indoor Object Recognition. IROS 2023: 3849-3856 - [c13]Donald Shenaj
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. WACV 2023: 444-454 - [i24]Elena Camuffo, Umberto Michieli
Learning from Mistakes: Self-Regularizing Hierarchical Semantic Representations in Point Cloud Segmentation. CoRR abs/2301.11145 (2023) - [i23]Umberto Michieli, Mete Özay:
Online Continual Learning for Robust Indoor Object Recognition. CoRR abs/2307.09827 (2023) - [i22]Edward Fish, Umberto Michieli
A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization. CoRR abs/2307.12659 (2023) - [i21]Umberto Michieli, Pablo Peso Parada, Mete Ozay:
Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics. CoRR abs/2307.12660 (2023) - [i20]Chang Liu, Giulia Rizzoli
RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation. CoRR abs/2309.10479 (2023) - 2022
- [j5]Umberto Michieli
Edge-Aware Graph Matching Network for Part-Based Semantic Segmentation. Int. J. Comput. Vis. 130(11): 2797-2821 (2022) - [j4]Donald Shenaj
Continual coarse-to-fine domain adaptation in semantic segmentation. Image Vis. Comput. 121: 104426 (2022) - [i19]Donald Shenaj, Francesco Barbato, Umberto Michieli, Pietro Zanuttigh:
Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation. CoRR abs/2201.06974 (2022) - [i18]Paolo Testolina
SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints. CoRR abs/2204.09788 (2022) - [i17]Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning. CoRR abs/2210.02326 (2022) - [i16]Marco Toldo, Umberto Michieli
Learning with Style: Continual Semantic Segmentation Across Tasks and Domains. CoRR abs/2210.07016 (2022) - 2021
- [j3]Umberto Michieli
Knowledge distillation for incremental learning in semantic segmentation. Comput. Vis. Image Underst. 205: 103167 (2021) - [c12]Umberto Michieli
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations. CVPR 2021: 1114-1124 - [c11]Umberto Michieli
Are All Users Treated Fairly in Federated Learning Systems? CVPR Workshops 2021: 2318-2322 - [c10]Francesco Barbato
Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation. CVPR Workshops 2021: 2835-2845 - [c9]Andrea Maracani, Umberto Michieli
RECALL: Replay-based Continual Learning in Semantic Segmentation. ICCV 2021: 7006-7015 - [c8]Marco Toldo, Umberto Michieli
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings. WACV 2021: 1357-1367 - [i15]Umberto Michieli, Pietro Zanuttigh:
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations. CoRR abs/2103.06342 (2021) - [i14]Francesco Barbato, Marco Toldo, Umberto Michieli, Pietro Zanuttigh:
Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation. CoRR abs/2104.02633 (2021) - [i13]Umberto Michieli, Mete Ozay:
Prototype Guided Federated Learning of Visual Feature Representations. CoRR abs/2105.08982 (2021) - [i12]Francesco Barbato, Umberto Michieli, Marco Toldo, Pietro Zanuttigh:
Adapting Segmentation Networks to New Domains by Disentangling Latent Representations. CoRR abs/2108.03021 (2021) - [i11]Andrea Maracani, Umberto Michieli, Marco Toldo, Pietro Zanuttigh:
RECALL: Replay-based Continual Learning in Semantic Segmentation. CoRR abs/2108.03673 (2021) - 2020
- [j2]Marco Toldo
Unsupervised domain adaptation for mobile semantic segmentation based on cycle consistency and feature alignment. Image Vis. Comput. 95: 103889 (2020) - [j1]Umberto Michieli
Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation. IEEE Trans. Intell. Veh. 5(3): 508-518 (2020) - [c7]Umberto Michieli
GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild. ECCV (8) 2020: 397-414 - [c6]Teo Spadotto, Marco Toldo
Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training. ICPR 2020: 2845-2852 - [i10]Marco Toldo, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh:
Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment. CoRR abs/2001.04692 (2020) - [i9]Teo Spadotto, Marco Toldo, Umberto Michieli, Pietro Zanuttigh:
Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training. CoRR abs/2004.12724 (2020) - [i8]Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh:
Unsupervised Domain Adaptation in Semantic Segmentation: a Review. CoRR abs/2005.10876 (2020) - [i7]Umberto Michieli, Edoardo Borsato, Luca Rossi, Pietro Zanuttigh:
GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild. CoRR abs/2007.09073 (2020) - [i6]Marco Toldo, Umberto Michieli, Pietro Zanuttigh:
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings. CoRR abs/2011.12616 (2020)
2010 – 2019
- 2019
- [c5]Matteo Biasetton, Umberto Michieli, Gianluca Agresti, Pietro Zanuttigh:
Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. CVPR Workshops 2019: 22-31 - [c4]Matteo Biasetton, Umberto Michieli
Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes. CVPR Workshops 2019: 1211-1220 - [c3]Umberto Michieli
Incremental Learning Techniques for Semantic Segmentation. ICCV Workshops 2019: 3205-3212 - [c2]Umberto Michieli
Region Merging Driven by Deep Learning for RGB-D Segmentation and Labeling. ICDSC 2019: 9:1-9:6 - [i5]Umberto Michieli, Pietro Zanuttigh:
Incremental Learning Techniques for Semantic Segmentation. CoRR abs/1907.13372 (2019) - [i4]Umberto Michieli, Matteo Biasetton, Gianluca Agresti, Pietro Zanuttigh:
Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation. CoRR abs/1909.00781 (2019) - [i3]Umberto Michieli, Pietro Zanuttigh:
Knowledge Distillation for Incremental Learning in Semantic Segmentation. CoRR abs/1911.03462 (2019) - 2018
- [c1]Umberto Michieli
Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles. PIMRC 2018: 1377-1381 - [i2]Umberto Michieli, Leonardo Badia:
Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles. CoRR abs/1803.02393 (2018) - [i1]Umberto Michieli:
Complex Network Analysis of Men Single ATP Tennis Matches. CoRR abs/1804.08138 (2018)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from ,
, and
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and
to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from .
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-11-19 20:44 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by: