Novelty detection for unsupervised continual learning in image sequences - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Novelty detection for unsupervised continual learning in image sequences

Résumé

Recent works in the domain of deep learning for object recognition on common image classification benchmarks often address the representation learning problem under the assumption of i.i.d. input data. Although achieving satisfying results, this assumption seems not realistic when agents have to learn autonomously. An autonomous agent receives a continual visual flow of objects which is far from an i.i.d. distribution of objects. Moreover, agents have to construct their representations of the world and adapt to unknown environments, without relying on external sources of information such as labels that would be provided post-classification and are unavoidable when an oversegmentation is done. Then, in order to exploit the learned representation effectively for object recognition, a clear and meaningful relationship w.r.t. real object categories is required, which has been largely neglected in existing unsupervised algorithms. In this paper, we propose a novelty detection method for continual and unsupervised object recognition, as an extension for the recent CURL model, which allows to moderate oversegmentation while preserving accuracy, in order to meet the requirements for autonomy. We experimentally validated our approach on two standard image classification benchmarks, MNIST and Fashion-MNIST, in this unsupervised and continual learning setting and improve the state of the art in terms of cluster purity, which is crucial for subsequent object recognition, since it facilitates clustering when information on ground truth labels is not available for free.
Fichier principal
Vignette du fichier
ICTAI_FINAL_submission.pdf (3.09 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03465146 , version 1 (03-12-2021)

Identifiants

Citer

Ruiqi Dai, Mathieu Lefort, Frédéric Armetta, Mathieu Guillermin, Stefan Duffner. Novelty detection for unsupervised continual learning in image sequences. IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Nov 2021, Washington DC (virtual), United States. ⟨10.1109/ICTAI52525.2021.00080⟩. ⟨hal-03465146⟩
109 Consultations
210 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More