Beyond solving static datasets: Deep learning from streaming data

Información del proyecto

KeepOnLearning

Identificador del acuerdo de subvención: 101021347

DOI

10.3030/101021347

Fecha de la firma de la CE 21 Agosto 2021

Fecha de inicio 1 Septiembre 2021

Fecha de finalización 31 Agosto 2026

Financiado con arreglo a

• EXCELLENT SCIENCE - European Research Council (ERC)

Coste total

€ 2 499 065,00

Aportación de la UE

€ 2 499 065,00

Coordinado por

KATHOLIEKE UNIVERSITEIT LEUVEN
Belgium

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (13)

Infinite dSprites for Disentangled Continual Learning: Separating Memory Edits from Generalization

Autores: Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
Publicado en: Third Conference on Lifelong Learning Agents (CoLLAs), Edición 29 July - 1 August 2024, 2024
Editor: CoLLAs

Prediction Error-based Classification for Class-Incremental Learning

Autores: Zając, Michał; Tuytelaars, Tinne; van de Ven, Gido M.
Publicado en: The 12th International Conference on Learning Representations (ICLR), Edición 7-11 May 2024, 2024
Editor: ICLR
DOI: 10.48550/arxiv.2305.18806

Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

Autores: Bo Wan, Wenjuan Han, Zilong Zheng, Tinne Tuytelaars
Publicado en: International Conference on Representation Learning, 2022
Editor: ICLR

Continual evaluation for lifelong learning: Identifying the stability gap

Autores: Matthias De Lange, Gido van de Ven, Tinne Tuytelaars
Publicado en: International Conference on Representation Learning, 2023
Editor: ICLR

Prediction Error-based Classification for Class-Incremental Learning

Autores: Michal Zajac, Tinne Tuytelaars, Gido van de Ven
Publicado en: Workshop on Continual Learning in Computer Vision, IEEE/CVF Conference on Computer Vision and Pattern Recognition, workshops, 2023
Editor: IEEE/CVF

(Deep) Generative Geodesics

Autores: Beomsu Kim, Michael Puthawala, Jong Chul Ye, Emanuele Sansone
Publicado en: ICML 2024 Workshop on Geometry-Grounded Representation Learning and Generative Modelling, Edición 27 July 2024, 2024
Editor: ICML

Exploiting CLIP for Zero-shot HOI Detection Requires Knowledge Distillation at Multiple Levels

Autores: Wan, Bo; Tuytelaars, Tinne
Publicado en: Winter Conference on Applications of Computer Vision, Edición 3-7 January 2024, 2024
Editor: IEEE/CVF
DOI: 10.48550/arxiv.2309.05069

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

Autores: Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
Publicado en: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Edición 18-22 June 2023, 2023
Editor: IEEE / CVF

Global-Local Self-Distillation for Visual Representation Learning

Autores: Tim Lebailly, Tinne Tuytelaars
Publicado en: Winter Conference on Applications of Computer Vision, 2023, Página(s) 1441-1450
Editor: IEEE / CVF

Continual Learning of Diffusion Models with Generative Distillation

Autores: Masip, Sergi; Rodriguez, Pau; Tuytelaars, Tinne; van de Ven, Gido M.
Publicado en: Third Conference on Lifelong Learning Agents (CoLLAs), Edición 29 July - 1 August 2024, 2024
Editor: CoLLAs
DOI: 10.48550/arxiv.2311.14028

NeVRF: Neural Video-based Radiance Fields for Long-duration Sequences

Autores: Wu, Minye; Tuytelaars, Tinne
Publicado en: International Conference on 3D Vision 2024, 2024
Editor: 3DV
DOI: 10.48550/arxiv.2312.05855

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

Autores: Lebailly, Tim; Stegmüller, Thomas; Bozorgtabar, Behzad; Thiran, Jean-Philippe; Tuytelaars, Tinne
Publicado en: International Conference on Computer Vision (ICCV), Edición 2-6 October 2023, 2023
Editor: IEEE/CVF
DOI: 10.1109/iccv51070.2023.01513

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

Autores: Lebailly, Tim; Stegmüller, Thomas; Bozorgtabar, Behzad; Thiran, Jean-Philippe; Tuytelaars, Tinne
Publicado en: The 12th International Conference on Learning Representations (ICLR), Edición 7-11 May 2024, 2024
Editor: ICLR
DOI: 10.48550/arxiv.2310.07855

Peer reviewed articles (3)

Three types of incremental learning

Autores: Gido van de Ven, Tinne Tuytelaars, Andreas S. Tolias
Publicado en: Nature Machine Intelligence, 2022, ISSN 2522-5839
Editor: Nature
DOI: 10.1038/s42256-022-00568-3

Continual Learning: Applications and the road forward

Autores: Eli Verwimp, Rahaf Aljundi, Shai Ben-David, Matthias Bethge, Andrea Cossu, Alexander Gepperth, Tyler L. Hayes, Eyke Hüllermeier, Christopher Kanan, Dhireesha Kudithipudi, Christoph H. Lampert, Martin Mundt, Razvan Pascanu, Adrian Popescu, Andreas S. Tolias, Joost van de Weijer, Bing Liu, Vincenzo Lomonaco, Tinne Tuytelaars, Gido van de Ven
Publicado en: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editor: JMLR

Knowledge Accumulation in Continually Learned Representations and the Issue of Feature Forgetting

Autores: Hess, Timm; Verwimp, Eli; van de Ven, Gido M.; Tuytelaars, Tinne
Publicado en: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editor: JMLR
DOI: 10.48550/arxiv.2304.00933

Other (1)

Two Complementary Perspectives to Continual Learning: Ask Not Only What to Optimize, But Also How

Autores: Hess, Timm; Tuytelaars, Tinne; van de Ven, Gido M.
Publicado en: arXiv, 2024
Editor: arXiv.org
DOI: 10.48550/arxiv.2311.04898