127 citations · 193 across the 15 of their papers we have counts for
15 papers
Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
Angelo Porrello, Pietro Buzzega, Felix Dangel +4
Task Arithmetic yields a modular, scalable way to adapt foundation models. Combining multiple task vectors, however, can lead to cross-task interference, causing representation dri…
Modular Embedding Recomposition for Incremental Learning
Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega +3
The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficie…
Update Your Transformer to the Latest Release: Re-Basin of Task Vectors
Filippo Rinaldi, Giacomo Capitani, Lorenzo Bonicelli +6
Foundation models serve as the backbone for numerous specialized models developed through fine-tuning. However, when the underlying pretrained model is updated or retrained (e.g.,…
May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
Monica Millunzi, Lorenzo Bonicelli, Angelo Porrello +3
Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data…
An Attention-based Representation Distillation Baseline for Multi-Label Continual Learning
Martin Menabue, Emanuele Frascaroli, Matteo Boschini +3
The field of Continual Learning (CL) has inspired numerous researchers over the years, leading to increasingly advanced countermeasures to the issue of catastrophic forgetting. Mos…
CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning
Emanuele Frascaroli, Aniello Panariello, Pietro Buzzega +3
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 Learni…
A Second-Order Perspective on Model Compositionality and Incremental Learning
Angelo Porrello, Lorenzo Bonicelli, Pietro Buzzega +3
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…
Semantic Residual Prompts for Continual Learning
Martin Menabue, Emanuele Frascaroli, Matteo Boschini +4
Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. Most of these methods organize these vectors in…
On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning
Lorenzo Bonicelli, Matteo Boschini, Emanuele Frascaroli +6
Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically. Continual Learning (CL) approaches seek to bridge this gap by facil…
On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
Lorenzo Bonicelli, Matteo Boschini, Angelo Porrello +2
Rehearsal approaches enjoy immense popularity with Continual Learning (CL) practitioners. These methods collect samples from previously encountered data distributions in a small me…
Spotting Virus from Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks
Lorenzo Bonicelli, Angelo Porrello, Stefano Vincenzi +4
The occurrence of West Nile Virus (WNV) represents one of the most common mosquito-borne zoonosis viral infections. Its circulation is usually associated with climatic and environm…
Transfer without Forgetting
Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello +5
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL). In particular, we shed light on the widespread application of network pretrainin…
Effects of Auxiliary Knowledge on Continual Learning
Giovanni Bellitto, Matteo Pennisi, Simone Palazzo +4
In Continual Learning (CL), a neural network is trained on a stream of data whose distribution changes over time. In this context, the main problem is how to learn new information…
Class-Incremental Continual Learning into the eXtended DER-verse
Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega +2
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, th…
Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
Matteo Boschini, Pietro Buzzega, Lorenzo Bonicelli +2
Continual Learning (CL) investigates how to train Deep Networks on a stream of tasks without incurring forgetting. CL settings proposed in literature assume that every incoming exa…