2 papers
cs.CV2023
On the challenges to learn from Natural Data Streams
Guido Borghi, Gabriele Graffieti, Davide Maltoni
In real-world contexts, sometimes data are available in form of Natural Data Streams, i.e. data characterized by a streaming nature, unbalanced distribution, data drift over a long…
cs.LG2021
Is Class-Incremental Enough for Continual Learning?
Andrea Cossu, Gabriele Graffieti, Lorenzo Pellegrini +4
The ability of a model to learn continually can be empirically assessed in different continual learning scenarios. Each scenario defines the constraints and the opportunities of th…