Semi-Supervised Class Incremental Learning

By Alexis Lechat, Stéphane Herbin, Frédéric Jurie. 2021

15 citations recorded by the source corpus.

This paper makes a contribution to the problem of incremental class learning, the principle of which is to sequentially introduce batches of samples annotated with new classes during the learning phase. The main objective is to reduce the drop in classification performance on old classes, a phenomenon commonly called catastrophic forgetting. We propose in this paper a new method which exploits the availability of a large quantity of non-annotated images in addition to the annotated batches. These images are used to regularize the classifier and give the feature space a more stable structure. We demonstrate on two image data sets, MNIST and STL-10, that our approach is able to improve the global performance of classifiers learned using an incremental learning protocol, even with annotated batches of small size.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Matteo Boschini
2. Simone Calderara
3. Lorenzo Bonicelli
4. Angelo Porrello
5. Elisa Ricci
6. Pietro Buzzega
7. Enrico Fini
8. Moin Nabi

In Computer Vision and Pattern Recognition

1. Simone Calderara
2. Matteo Boschini
3. Angelo Porrello
4. Lorenzo Bonicelli
5. Elisa Ricci
6. Enrico Fini
7. Moin Nabi
8. Pietro Buzzega

In Representation & Self-Supervised Learning

1. Matteo Boschini
2. Angelo Porrello
3. Lorenzo Bonicelli
4. Enrico Fini
5. Pietro Buzzega
6. Zhiqi Kang
7. Moin Nabi
8. Simone Calderara

In Meta & Continual Learning

1. Simone Calderara
2. Matteo Boschini
3. Lorenzo Bonicelli
4. Angelo Porrello
5. Elisa Ricci
6. Pietro Buzzega
7. Enrico Fini
8. Moin Nabi

Citations in the corpus

• A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, neutral): “Subsequent work includes training an adversarial autoencoder to reconstruct images [265], imposing predictive consistency among augmented and interpolated data [266], and leveraging the nearest-neighbor classifier to distill class-instance relationships [267].”
• A soft nearest-neighbor framework for continual semi-supervised learning (2022, background): “While the vast majority of these methods operate in a supervised setting, recent works addressed the problem of overcoming catastrophic forgetting in the challenging case of limited [8, 28, 44, 52] or no supervision [1, 21, 37, 45].”
• Continual semi-supervised learning through contrastive interpolation consistency (2021, methodology): “Alternatively, Lechat et al. introduced SemiSupervised Incremental Learning [14], which alternates unsupervised feature learning on both input and auxiliary data with supervised classification.”