1.7k citations · 1.9k across the 16 of their papers we have counts for
7 papers · 1 filter
One Loop, Two Gains: Can Active Learning win the Lottery for Free?
Benedikt Tscheschner, Eduardo Veas, Marc Masana
The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of…
Incremental Learning with Repetition via Pseudo-Feature Projection
Benedikt Tscheschner, Eduardo Veas, Marc Masana
Incremental Learning scenarios do not always represent real-world inference use-cases, which tend to have less strict task boundaries, and exhibit repetition of common classes and…
Leveraging Intermediate Representations for Better Out-of-Distribution Detection
Gianluca Guglielmo, Marc Masana
In real-world applications, machine learning models must reliably detect Out-of-Distribution (OoD) samples to prevent unsafe decisions. Current OoD detection methods often rely on…
Continual Learning in the Presence of Repetition
Hamed Hemati, Lorenzo Pellegrini, Xiaotian Duan +11
Continual learning (CL) provides a framework for training models in ever-evolving environments. Although re-occurrence of previously seen objects or tasks is common in real-world p…
On the importance of cross-task features for class-incremental learning
Albin Soutif--Cormerais, Marc Masana, Joost van de Weijer +1
In class-incremental learning, an agent with limited resources needs to learn a sequence of classification tasks, forming an ever growing classification problem, with the constrain…
Avalanche: an End-to-End Library for Continual Learning
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu +25
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing…
Class-incremental learning: survey and performance evaluation on image classification
Marc Masana, Xialei Liu, Bartlomiej Twardowski +3
For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new…