Gabriele Graffieti

2 accepted papers

2022

Continual Learning in Real-Life Applications

Gabriele Graffieti, Guido Borghi, Davide Maltoni

RA-L 2022

Existing Continual Learning benchmarks only partially address the complexity of real-life applications, limiting the realism of learning agents. In this letter, we propose and focus on benchmarks characterized by common key elements of real-life scenarios, including temporally ordered streams as inp

Cited by 20 Source ↗Scholar ↗

2020

Latent Replay for Real-Time Continual Learning

Lorenzo Pellegrini, Gabriele Graffieti, Vincenzo Lomonaco, Davide Maltoni

IROS 2020poster

Training deep neural networks at the edge on light computational devices, embedded systems and robotic platforms is nowadays very challenging. Continual learning techniques, where complex models are incrementally trained on small batches of new data, can make the learning problem tractable even for…

Cited by 201 Source ↗Scholar ↗