Is Class-Incremental Enough for Continual Learning?

by   Andrea Cossu, et al.

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 the learning environment. Here, we challenge the current trend in the continual learning literature to experiment mainly on class-incremental scenarios, where classes present in one experience are never revisited. We posit that an excessive focus on this setting may be limiting for future research on continual learning, since class-incremental scenarios artificially exacerbate catastrophic forgetting, at the expense of other important objectives like forward transfer and computational efficiency. In many real-world environments, in fact, repetition of previously encountered concepts occurs naturally and contributes to softening the disruption of previous knowledge. We advocate for a more in-depth study of alternative continual learning scenarios, in which repetition is integrated by design in the stream of incoming information. Starting from already existing proposals, we describe the advantages such class-incremental with repetition scenarios could offer for a more comprehensive assessment of continual learning models.


vCLIMB: A Novel Video Class Incremental Learning Benchmark

Continual learning (CL) is under-explored in the video domain. The few e...

PromptFusion: Decoupling Stability and Plasticity for Continual Learning

Continual learning refers to the capability of continuously learning fro...

Class-Incremental Learning with Repetition

Real-world data streams naturally include the repetition of previous con...

Class-Incremental Mixture of Gaussians for Deep Continual Learning

Continual learning models for stationary data focus on learning and reta...

ICICLE: Interpretable Class Incremental Continual Learning

Continual learning enables incremental learning of new tasks without for...

Susceptibility of Continual Learning Against Adversarial Attacks

The recent advances in continual (incremental or lifelong) learning have...

Three scenarios for continual learning

Standard artificial neural networks suffer from the well-known issue of ...

Please sign up or login with your details

Forgot password? Click here to reset