Zobrazeno 1 - 10
of 910
pro vyhledávání: '"Calderara, A."'
Autor:
Mancusi, Gianluca, Bernardi, Mattia, Panariello, Aniello, Porrello, Angelo, Cucchiara, Rita, Calderara, Simone
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets. However, training these trackers in heterogeneous scenarios poses significant challenges, including negative interference - where the model lea
Externí odkaz:
http://arxiv.org/abs/2411.00553
Autor:
Salami, Riccardo, Buzzega, Pietro, Mosconi, Matteo, Bonato, Jacopo, Sabetta, Luigi, Calderara, Simone
Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving performance and scalability. In this respect, the compositional properties of low-rank adaptation te
Externí odkaz:
http://arxiv.org/abs/2410.17961
Autor:
Millunzi, Monica, Bonicelli, Lorenzo, Porrello, Angelo, Credi, Jacopo, Kolm, Petter N., Calderara, Simone
Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments. To address this issue, most approaches in Continual Lear
Externí odkaz:
http://arxiv.org/abs/2408.14284
Autor:
Frascaroli, Emanuele, Panariello, Aniello, Buzzega, Pietro, Bonicelli, Lorenzo, Porrello, Angelo, Calderara, Simone
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting strategies t
Externí odkaz:
http://arxiv.org/abs/2407.15793
Autor:
Menabue, Martin, Frascaroli, Emanuele, Boschini, Matteo, Bonicelli, Lorenzo, Porrello, Angelo, Calderara, Simone
The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Most studies have focused on the single-class scenario, where each exampl
Externí odkaz:
http://arxiv.org/abs/2407.14249
Autor:
Mosconi, Matteo, Sorokin, Andriy, Panariello, Aniello, Porrello, Angelo, Bonato, Jacopo, Cotogni, Marco, Sabetta, Luigi, Calderara, Simone, Cucchiara, Rita
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively. Herein, we believe that exploring this problem within the context of Continual Learning is crucial. While numerous studies focus on skelet
Externí odkaz:
http://arxiv.org/abs/2407.01397
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data distribut
Externí odkaz:
http://arxiv.org/abs/2406.02447
Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e.g. basketball players engaged in intricate interactions with long-term intentions. Deep generative models of
Externí odkaz:
http://arxiv.org/abs/2405.20743
Autor:
Porrello, Angelo, Bonicelli, Lorenzo, Buzzega, Pietro, Millunzi, Monica, Calderara, Simone, Cucchiara, Rita
The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model. However, identifying the conditions that promote compositionality re
Externí odkaz:
http://arxiv.org/abs/2405.16350
Autor:
Bellitto, Giovanni, Salanitri, Federica Proietto, Pennisi, Matteo, Boschini, Matteo, Porrello, Angelo, Calderara, Simone, Palazzo, Simone, Spampinato, Concetto
We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting. Inspired by neurophysiological evidence that the primary visual cortex does not contribute to ob
Externí odkaz:
http://arxiv.org/abs/2403.20086