I am a Senior AI Researcher at Samsung Research UK where I serve as the tech lead for on-device personalized AI projects.
I contribute to the adoption of AI in everyday life and to its adaptation to meet users' needs.
My interests broadly lie at the intersection of foundation AI problems (e.g., Continual Learning, Domain Adaptation, Distributed/Federated Learning, Model Compression, Streaming Learning, Model Robustness,...) applied to several end tasks.
Our group at Samsung UK is often looking for good research intern / full-time candidates. Feel free to reach out if you are interested in working with us!
Check out the publications section and my Google Scholar profile to know more about my work.
2023 - This section will not be updated. Please check my Google Scholar for an updated list of works.
5 patents filed in late 2022 and early 2023.
[J11] Camuffo E., Michieli U., Milani S., “Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation,” IEEE Transactions on Multimedia (TMM), 2024. [link]
[J10] Testolina P., Barbato F., Michieli U., Giordani M., Zanuttigh P., and Zorzi M., “SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Day-time and Viewpoints,” IEEE Transactions on Intelligent Transportation Systems (T-ITS), 2023. [link]
[J9] Barbato F., Michieli U., Toldo M., and Zanuttigh P., “Road scenes segmentation across different domains by disentangling latent representations,” Springer The Visual Computer Journal (TVCJ), 2023. [link]
[J8] Michieli U., Toldo M. and Ozay M., “Federated Learning via Attentive Margin of Semantic Feature Representations”, IEEE Internet of Things Journal (IoTJ), 2022. [link]
[J7] Michieli U. and Zanuttigh P., “Edge-aware graph matching network for part-based semantic segmentation”, International Journal of Computer Vision (IJCV), 2022. [link]
[J6] Shenaj D., Barbato F., Michieli U. and Zanuttigh P., "Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation", Elsevier Image and Vision Computing (IMAVIS), 2022. [PDF]
[J5] Michieli U. and Zanuttigh P., "Knowledge Distillation for Incremental Learning in Semantic Segmentation", Elsevier Computer Vision and Image Understanding (CVIU), 2021. [PDF]
[J4] Toldo M., Maracani A., Michieli U., Zanuttigh P., "Unsupervised Domain Adaptation in Semantic Segmentation: a Review", Technologies, 2020, 8, 35. [PDF]
[J3] Michieli U., Biasetton M., Agresti G., Zanuttigh P., "Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation", IEEE Transactions on Intelligent Vehicles (T-IV), 2020. [PDF] [webpage] [link]
[J2] Mel M., Michieli U., Zanuttigh P., "Incremental and Multi-Task Learning Strategies for Coarse-To-Fine Semantic Segmentation", Technologies, special issue on Computer Vision and Image Processing Technologies 2020, 8, 1. [PDF] [link]
[J1] Toldo M., Michieli U., Agesti G., Zanuttigh P., "Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment", Elsevier Image and Vision Computing (IMAVIS), 2020. [link] [webpage]
[C22] Michieli U., Ozay M., “HOP to the Next Tasks and Domains for Continual Learning in NLP,” AAAI Conference on Artificial Intelligence (AAAI), 2024
[C21] Michieli U., Moon J., Kim D., Ozay M., “Object-Conditioned Bag of Instances for Few-Shot Personalized Instance Recognition,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
[C20] Tiomoko Ali H., Michieli U., Moon J., Kim D., Ozay M., “Deep Neural Network Models Trained With A Fixed Random Classifier Transfer Better Across Domains,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
[C19] Camuffo E., Michieli U., Moon J., Kim D., Ozay M., “FFT-based Selection And Optimization Of Statistics For Robust Recognition Of Severely Corrupted Images,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024
[C18] Campagnolo D., Camuffo E., Michieli U., Borin P., Milani S., Giordano A., “Fully Automated Scan-to-BIM Via Point Cloud Instance Segmentation,” ICIP, 2023. [link] [code] [dataset]
[C17] Michieli U., Ozay M., “Online Continual Learning for Robust Indoor Object Recognition,” IROS, 2023. [link] [slides] [poster]
[C16] Michieli U., Parada P. P., Ozay M., “Online Continual Learning in Keyword Spotting for Low-Resource Devices via Pooling High-Order Temporal Statistics,” INTERSPEECH, 2023. [link] [slides] [splits]
[C15] Fish E., Michieli U., Ozay M., “A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization,” INTERSPEECH, 2023. [link] [poster] [code]
[C14] Stewart J., Michieli U., Ozay M., “Data-Free Model Pruning at Initialization via Expanders,” Computer Vision and Pattern Recognition Workshop (CVPRW) on Efficient Computer Vision (ECV), 2023. [link] [poster]
[C13] Shenaj D.*, Fanì E.*, Toldo M., Caldarola D., Tavera A., Michieli U.*, Ciccone M.*, Zanuttigh P.*, Caputo B.*, “Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning,” Winter Conference on Applications of Computer Vision (WACV), 2023. [link]
[C12] Maracani A.*, Michieli U.*, Toldo M.* and Zanuttigh P. "RECALL: Replay-based Continual Learning in Semantic Segmentation", Proceedings of the International Computer Vision Conference (ICCV), 2021. [paper] [code] [poster]
[C11] Michieli U., Ozay M., "Are All Users Treated Fairly in Federated Learning Systems?", Proceedings of the Computer Vision and Pattern Recognition (CVPR) Conference, Workshop on Responsible Computer Vision (RCV), 2021. [paper] [talk] [poster] [slides]
[C10] Barbato F., Toldo M., Michieli U., Zanuttigh P., "Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation", Proceedings of the Computer Vision and Pattern Recognition (CVPR) Conference, Workshop on Autonomous Driving (WAD), 2021. [PDF] [poster] [webpage]
[C9] Michieli U., Zanuttigh P., "Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations", Proceedings of the Computer Vision and Pattern Recognition (CVPR) Conference, 19-25 June 2021. [paper] [talk] [poster] [slides] [webpage] [code]
[C8] Toldo M., Michieli U., Zanuttigh P., "Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings", Proceedings of the Winter Conference on Applications of Computer Vision (WACV), 05-09 January 2021. [link] [slides] [talk] [webpage] [code]
[C7] Michieli U., Borsato E., Rossi L., Zanuttigh P., "GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild", Proceedings of the European Conference on Computer Vision (ECCV), Glasgow (UK), 23-28 August 2020. [PDF] [webpage] [code] [slides 1 min] [talk 1 min] [slides 10 mins] [talk 10 mins]
[C6] Spadotto T., Toldo M., Michieli U., Zanuttigh P., "Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training", Proceedings of the International Conference on Pattern Recognition (ICPR), Milan (Italy), 10-15 January 2020. [PDF] [webpage + code] [slides] [poster] [talk]
[C5] Michieli U., Zanuttigh P., "Incremental Learning Techniques for Semantic Segmentation", Proceedings of the International Conference on Computer Vision (ICCV), Workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), Seoul (South Korea), 2 November 2019. [webpage] [PDF] [poster] [code]
[C4] Michieli U., Camporese M., Agiollo A., Pagnutti G., Zanuttigh P., "Region Merging Driven by Deep Learning for RGB-D Segmentation and Labeling", Proceedings of the International Conference on Distributed Smart Cameras (ICDSC), Trento (Italy), 9-11 September 2019. [link] [slides]
[C3] Biasetton M., Michieli U., Agresti G., Zanuttigh P., "Unsupervised Domain Adaptation for Semantic Segmentation of Urban Scenes", Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Autonomous Driving (WAD), Long Beach (USA), 17 June 2019. [link] [PDF] [posterICVSS2019] [posterCVPRW2019] [webpage]
[C2] Michieli U., Badia L., "Game Theoretic Analysis of Road User Safety Scenarios Involving Autonomous Vehicles", IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC), Bologna (Italy), pages 1377-1381, 9-12 September 2018. [link] [PDF] [slides]
[C1] Cisotto G., Michieli U., Badia L., "A Coherence Study on EEG and EMG Signals", Proceedings of the Global Wireless Summit (GWS), Aarhus (Denmark), pages 372–376, December 2016, e-ISBN: 9788793609297. [PDF] [slides]
[B1] Michieli U., Toldo M., Zanuttigh P., "Unsupervised Domain Adaptation and Continual Learning in Semantic Segmentation", Advanced Methods and Deep Learning in Computer Vision, Elsevier, 2021. [link]
[PO4] Testolina P., Barbato F., Michieli U., Giordani M., Zanuttigh P., and Zorzi M., “SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Day-time and Viewpoints for Autonomous Driving Research,” 6G Summit, 2023.
[PO3] Testolina P., Barbato F., Michieli U., Giordani M., Zanuttigh P., and Zorzi M., “SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Day-time and Viewpoints for Autonomous Driving Research,” European Conference on Networks and Communications (EuCNC), 2022.
[PO2] Michieli U., Testolina P., Lecci M., Zorzi M. "Wireless User Positioning via Synthetic Data Augmentation and Smart Ensembling", IEEE Communication Theory Workshop (CTW), May 26-29, 2019, Selfoss (Iceland). [PDF]
[PO1] Michieli U., Muscoloni A., Badia L., Cannistraci C.V. "A dramatic truth in link prediction: SBM inference fails to effectively predict even the structure of synthetic networks generated with the SBM model", Complex Networks 2018: the 7th International Conference on Complex Networks and Their Applications, December 11-13, 2018, Cambridge (United Kingdom). [PDF]
[PhD] Michieli U., "Visual Understanding across Semantic Groups, Domains and Devices", Ph.D. Thesis in Information Engineering, Department of Information Engineering, University of Padova, September 2021. [link]
[MSc] Michieli U., "Link Prediction on Real and Synthetic Complex Networks", MS Thesis in Telecommunication Engineering, Department of Information Engineering, University of Padova, September 2018. [PDF] [LaTeX template] [slides] [template slides]
[BSc] Michieli U., "Correlation and Coherence Analysis between EEG and EMG signals", BS Thesis in Information Engineering, Department of Information Engineering, University of Padova, July 2016. [PDF] [LaTeX template] [slides] [template slides]
Visit my profile on Google Scholar: Umberto Michieli
