Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Belgium

Marie Skłodowska-Curie Action · Finished

GenClassifier4CL Incrementally learning new classes with generative classification

Coordinator
Katholieke Universiteit Leuven, Belgium
Runs
1 October 2022 to 30 September 2024
Status
Finished
EU funding
€192k
Total cost
—
Partners
1 organisations in 1 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101067759

What the project is doing

In the project's own words, from its summary on CORDIS.

Learning continually from non-stationary streams of data is a key feature of natural intelligence, but an unsolved problem in deep learning. Particularly challenging for deep neural networks is the problem of ""class-incremental learning"", whereby a network must learn to distinguish classes that are not observed together. In deep learning, the default approach to classification is learning discriminative classifiers.

This works great in the i.i.d. setting when all classes are available simultaneously, but when new classes must be learned incrementally, successful training of discriminative classifiers depends on workarounds such as storing data or generative replay. In a radical shift of gears, here I propose to instead address class-incremental learning with generative classification. Key advantage is that generative classifiers – unlike discriminative classifiers – do not compare classes during training, but only during inference (i.e., when making a classification decision).

As a proof-of-concept, in preliminary work I showed that a naïve implementation of a generative classifier, with a separate variational autoencoder model per class and likelihood estimation through importance sampling, outperforms comparable generative replay methods. To improve the efficiency, scalability, and performance of this generative classifier, I propose four further modifications: (1) move the generative modelling objective from the raw inputs to an intermediate network layer

Topics

Who is involved

OrganisationCityCountryRole
Katholieke Universiteit LeuvenLeuvenBelgiumCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI