Beyond solving static datasets: Deep learning from streaming data

Informazioni relative al progetto

KeepOnLearning

ID dell’accordo di sovvenzione: 101021347

DOI

10.3030/101021347

Data della firma CE 21 Agosto 2021

Data di avvio 1 Settembre 2021

Data di completamento 31 Agosto 2026

Finanziato da

• EXCELLENT SCIENCE - European Research Council (ERC)

Costo totale

€ 2 499 065,00

Contributo UE

€ 2 499 065,00

Coordinato da

KATHOLIEKE UNIVERSITEIT LEUVEN
Belgium

CORDIS fornisce collegamenti ai risultati finali pubblici e alle pubblicazioni dei progetti ORIZZONTE.

I link ai risultati e alle pubblicazioni dei progetti del 7° PQ, così come i link ad alcuni tipi di risultati specifici come dataset e software, sono recuperati dinamicamente da .OpenAIRE .

Pubblicazioni

Conference proceedings (13)

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

Autori: Sebastian Dziadzio, Çağatay Yıldız, Gido M. van de Ven, Tomasz Trzciński, Tinne Tuytelaars, Matthias Bethge
Pubblicato in: Third Conference on Lifelong Learning Agents (CoLLAs), Numero 29 July - 1 August 2024, 2024
Editore: CoLLAs

Prediction Error-based Classification for Class-Incremental Learning

Autori: Zając, Michał; Tuytelaars, Tinne; van de Ven, Gido M.
Pubblicato in: The 12th International Conference on Learning Representations (ICLR), Numero 7-11 May 2024, 2024
Editore: ICLR
DOI: 10.48550/arxiv.2305.18806

Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling

Autori: Bo Wan, Wenjuan Han, Zilong Zheng, Tinne Tuytelaars
Pubblicato in: International Conference on Representation Learning, 2022
Editore: ICLR

Continual evaluation for lifelong learning: Identifying the stability gap

Autori: Matthias De Lange, Gido van de Ven, Tinne Tuytelaars
Pubblicato in: International Conference on Representation Learning, 2023
Editore: ICLR

Prediction Error-based Classification for Class-Incremental Learning

Autori: Michal Zajac, Tinne Tuytelaars, Gido van de Ven
Pubblicato in: Workshop on Continual Learning in Computer Vision, IEEE/CVF Conference on Computer Vision and Pattern Recognition, workshops, 2023
Editore: IEEE/CVF

(Deep) Generative Geodesics

Autori: Beomsu Kim, Michael Puthawala, Jong Chul Ye, Emanuele Sansone
Pubblicato in: ICML 2024 Workshop on Geometry-Grounded Representation Learning and Generative Modelling, Numero 27 July 2024, 2024
Editore: ICML

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

Autori: Wan, Bo; Tuytelaars, Tinne
Pubblicato in: Winter Conference on Applications of Computer Vision, Numero 3-7 January 2024, 2024
Editore: IEEE/CVF
DOI: 10.48550/arxiv.2309.05069

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

Autori: Thomas Stegmüller, Tim Lebailly, Behzad Bozorgtabar, Tinne Tuytelaars, Jean-Philippe Thiran
Pubblicato in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, Numero 18-22 June 2023, 2023
Editore: IEEE / CVF

Global-Local Self-Distillation for Visual Representation Learning

Autori: Tim Lebailly, Tinne Tuytelaars
Pubblicato in: Winter Conference on Applications of Computer Vision, 2023, Pagina/e 1441-1450
Editore: IEEE / CVF

Continual Learning of Diffusion Models with Generative Distillation

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

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

Autori: Wu, Minye; Tuytelaars, Tinne
Pubblicato in: International Conference on 3D Vision 2024, 2024
Editore: 3DV
DOI: 10.48550/arxiv.2312.05855

Adaptive Similarity Bootstrapping for Self-Distillation based Representation Learning

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

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

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

Peer reviewed articles (3)

Three types of incremental learning

Autori: Gido van de Ven, Tinne Tuytelaars, Andreas S. Tolias
Pubblicato in: Nature Machine Intelligence, 2022, ISSN 2522-5839
Editore: Nature
DOI: 10.1038/s42256-022-00568-3

Continual Learning: Applications and the road forward

Autori: 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
Pubblicato in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editore: JMLR

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

Autori: Hess, Timm; Verwimp, Eli; van de Ven, Gido M.; Tuytelaars, Tinne
Pubblicato in: Transactions on Machine Learning Research, 2024, ISSN 2835-8856
Editore: JMLR
DOI: 10.48550/arxiv.2304.00933

Other (1)

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

Autori: Hess, Timm; Tuytelaars, Tinne; van de Ven, Gido M.
Pubblicato in: arXiv, 2024
Editore: arXiv.org
DOI: 10.48550/arxiv.2311.04898