Beyond solving static datasets: Deep learning from streaming data

Project Information

KeepOnLearning

Grant agreement ID: 101021347

DOI

10.3030/101021347

EC signature date 21 August 2021

Start date 1 September 2021

End date 31 August 2026

Funded under

• EXCELLENT SCIENCE - European Research Council (ERC)

Total cost

€ 2 499 065,00

EU contribution

€ 2 499 065,00

Coordinated by

KATHOLIEKE UNIVERSITEIT LEUVEN
Belgium

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (13)

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

Author(s): Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
Published in: Third Conference on Lifelong Learning Agents (CoLLAs), Issue 29 July - 1 August 2024, 2024
Publisher: CoLLAs

Prediction Error-based Classification for Class-Incremental Learning

Author(s): Zając, Michał; Tuytelaars, Tinne; van de Ven, Gido M.
Published in: The 12th International Conference on Learning Representations (ICLR), Issue 7-11 May 2024, 2024
Publisher: ICLR
DOI: 10.48550/arxiv.2305.18806

Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

Author(s): Bo Wan, Wenjuan Han, Zilong Zheng, Tinne Tuytelaars
Published in: International Conference on Representation Learning, 2022
Publisher: ICLR

Continual evaluation for lifelong learning: Identifying the stability gap

Author(s): Matthias De Lange, Gido van de Ven, Tinne Tuytelaars
Published in: International Conference on Representation Learning, 2023
Publisher: ICLR

Prediction Error-based Classification for Class-Incremental Learning

Author(s): Michal Zajac, Tinne Tuytelaars, Gido van de Ven
Published in: Workshop on Continual Learning in Computer Vision, IEEE/CVF Conference on Computer Vision and Pattern Recognition, workshops, 2023
Publisher: IEEE/CVF

(Deep) Generative Geodesics

Author(s): Beomsu Kim, Michael Puthawala, Jong Chul Ye, Emanuele Sansone
Published in: ICML 2024 Workshop on Geometry-Grounded Representation Learning and Generative Modelling, Issue 27 July 2024, 2024
Publisher: ICML

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

Author(s): Wan, Bo; Tuytelaars, Tinne
Published in: Winter Conference on Applications of Computer Vision, Issue 3-7 January 2024, 2024
Publisher: IEEE/CVF
DOI: 10.48550/arxiv.2309.05069

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

Author(s): Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
Published in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Issue 18-22 June 2023, 2023
Publisher: IEEE / CVF

Global-Local Self-Distillation for Visual Representation Learning

Author(s): Tim Lebailly, Tinne Tuytelaars
Published in: Winter Conference on Applications of Computer Vision, 2023, Page(s) 1441-1450
Publisher: IEEE / CVF

Continual Learning of Diffusion Models with Generative Distillation

Author(s): Masip, Sergi; Rodriguez, Pau; Tuytelaars, Tinne; van de Ven, Gido M.
Published in: Third Conference on Lifelong Learning Agents (CoLLAs), Issue 29 July - 1 August 2024, 2024
Publisher: CoLLAs
DOI: 10.48550/arxiv.2311.14028

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

Author(s): Wu, Minye; Tuytelaars, Tinne
Published in: International Conference on 3D Vision 2024, 2024
Publisher: 3DV
DOI: 10.48550/arxiv.2312.05855

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

Author(s): Lebailly, Tim; Stegmüller, Thomas; Bozorgtabar, Behzad; Thiran, Jean-Philippe; Tuytelaars, Tinne
Published in: International Conference on Computer Vision (ICCV), Issue 2-6 October 2023, 2023
Publisher: IEEE/CVF
DOI: 10.1109/iccv51070.2023.01513

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

Author(s): Lebailly, Tim; Stegmüller, Thomas; Bozorgtabar, Behzad; Thiran, Jean-Philippe; Tuytelaars, Tinne
Published in: The 12th International Conference on Learning Representations (ICLR), Issue 7-11 May 2024, 2024
Publisher: ICLR
DOI: 10.48550/arxiv.2310.07855

Peer reviewed articles (3)

Three types of incremental learning

Author(s): Gido van de Ven, Tinne Tuytelaars, Andreas S. Tolias
Published in: Nature Machine Intelligence, 2022, ISSN 2522-5839
Publisher: Nature
DOI: 10.1038/s42256-022-00568-3

Continual Learning: Applications and the road forward

Author(s): 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
Published in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Publisher: JMLR

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

Author(s): Hess, Timm; Verwimp, Eli; van de Ven, Gido M.; Tuytelaars, Tinne
Published in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Publisher: JMLR
DOI: 10.48550/arxiv.2304.00933

Other (1)

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

Author(s): Hess, Timm; Tuytelaars, Tinne; van de Ven, Gido M.
Published in: arXiv, 2024
Publisher: arXiv.org
DOI: 10.48550/arxiv.2311.04898