Simone Magistri

21 papers A* 2Journal 14Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Color Is Not Enough: Dataset and Method for Identifying Relevant Traffic Lights in Driving Scenes.
IEEE Trans. Intell. Transp. Syst.
Tomaso Trinci, Simone Magistri, Tommaso Bianconcini, Leonardo Taccari, Leonardo Sarti, Francesco Sambo
2026 J jnl
Cross-Modal Prototype Alignment and Mixing for Training-Free Few-Shot Classification.
CoRR
Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bartlomiej Twardowski, Andrew D. Bagdanov, Tinne Tuytelaars, Joost van de Weijer
2026 J jnl
IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment.
CoRR
Simone Magistri, Dipam Goswami, Marco Mistretta, Bartlomiej Twardowski, Joost van de Weijer, Andrew D. Bagdanov
2026 J jnl
SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery.
CoRR
Lorenzo Caselli, Marco Mistretta, Simone Magistri, Andrew D. Bagdanov
2025 J jnl
A Bi-Objective Optimization Based Acquisition Strategy for Batch Bayesian Global Optimization.
Comput. Optim. Appl.
Francesco Carciaghi, Simone Magistri, Pierluigi Mansueto, Fabio Schoen
2025 J jnl
Accurate and Efficient Low-Rank Model Merging in Core Space.
CoRR
Aniello Panariello, Daniel Marczak, Simone Magistri, Angelo Porrello, Bartlomiej Twardowski, Andrew D. Bagdanov, Simone Calderara, Joost van de Weijer
2025 J jnl
EFC++: Elastic Feature Consolidation with Prototype Re-balancing for Cold Start Exemplar-free Incremental Learning.
CoRR
Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov
2025 A* conf
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces.
ICML
Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2025 J jnl
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces.
CoRR
Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2024 — conf
An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates.
CoLLAs
Albin Soutif, Simone Magistri, Joost van de Weijer, Andrew D. Bagdanov
2024 J jnl
An Empirical Analysis of Forgetting in Pre-trained Models with Incremental Low-Rank Updates.
CoRR
Albin Soutif-Cormerais, Simone Magistri, Joost van de Weijer, Andrew D. Bagdanov
2024 J jnl
Continual learning for adaptive social network identification.
Pattern Recognit. Lett.
Simone Magistri, Daniele Baracchi, Dasara Shullani, Andrew D. Bagdanov, Alessandro Piva
2024 J jnl
Covariances for Free: Exploiting Mean Distributions for Federated Learning with Pre-Trained Models.
CoRR
Dipam Goswami, Simone Magistri, Kai Wang, Bartlomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer
2024 A* conf
Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning.
ICLR
Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov
2024 J jnl
Elastic Feature Consolidation for Cold Start Exemplar-free Incremental Learning.
CoRR
Simone Magistri, Tomaso Trinci, Albin Soutif-Cormerais, Joost van de Weijer, Andrew D. Bagdanov
2024 — conf
How Green Is Continual Learning, Really? Analyzing the Energy Consumption in Continual Training of Vision Foundation Models.
ECCV Workshops (22)
Tomaso Trinci, Simone Magistri, Roberto Verdecchia, Andrew D. Bagdanov
2024 J jnl
How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models.
CoRR
Tomaso Trinci, Simone Magistri, Roberto Verdecchia, Andrew D. Bagdanov
2024 — conf
Incremental and Decremental Continual Learning for Privacy-Preserving Video Recognition.
ECCV Workshops (21)
Lorenzo Caselli, Simone Magistri, Tommaso Bianconcini, Andrea Benericetti, Douglas Coimbra de Andrade, Andrew D. Bagdanov
2023 J jnl
Lightweight and Effective Convolutional Neural Networks for Vehicle Viewpoint Estimation From Monocular Images.
IEEE Trans. Intell. Transp. Syst.
Simone Magistri, Marco Boschi, Francesco Sambo, Douglas Coimbra de Andrade, Matteo Simoncini, Luca Kubin, Leonardo Taccari, Luca De Luigi, Samuele Salti
2023 — conf
Towards Continual Social Network Identification.
IWBF
Simone Magistri, Daniele Baracchi, Dasara Shullani, Andrew D. Bagdanov, Alessandro Piva
2020 — conf
A Lightweight Deep Learning Model for Vehicle Viewpoint Estimation from Dashcam Images.
ITSC
Simone Magistri, Francesco Sambo, Fabio Schoen, Douglas Coimbra de Andrade, Matteo Simoncini, Stefano Caprasecca, Luca Kubin, Luca Bravi, Leonardo Taccari