Deep Online Storage-Free Learning on Unordered Image Streams - Archive ouverte HAL Access content directly
Poster Communications Year : 2019

Deep Online Storage-Free Learning on Unordered Image Streams

Abstract

In this work we develop an online deep-learning based approach for classification on data streams. Our approach is able to learn in an incremental way without storing and reusing the historical data (we only store a recent history) while processing each new data sample only once. To make up for the absence of the historical data, we train Generative Adversarial Networks (GANs), which, in recent years have shown their excellent capacity to learn data distributions for image datasets. We test our approach on MNIST and LSUN datasets and demonstrate its ability to adapt to previously unseen data classes or new instances of previously seen classes, while avoiding forgetting of previously learned classes/instances of classes that do not appear anymore in the data stream.
Fichier principal
Vignette du fichier
poster_AndreyBesedin.pdf (1.8 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02454302 , version 1 (13-06-2022)

Identifiers

Cite

Andrey Besedin, Pierre Blanchart, Michel Crucianu, Marin Ferecatu. Deep Online Storage-Free Learning on Unordered Image Streams. Springer; Anna Monreale, Carlos Alzate, Michael Kamp, Yamuna Krishnamurthy, Daniel Paurat, Moamar Sayed-Mouchaweh, Albert Bifet, João Gama, Rita P. Ribeiro. ECML PKDD: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Sep 2018, Dublin, Ireland. 967, pp.103-112, 2019, Communications in Computer and Information Science - ECML PKDD 2018 Workshops. ⟨10.1007/978-3-030-14880-5_9⟩. ⟨hal-02454302⟩
88 View
12 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More