Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Joost van de Weijer

Continually Learning Self-Supervised Representations with Projected Functional Regularization


Dec 30, 2021
Alex Gomez-Villa, Bartlomiej Twardowski, Lu Yu, Andrew D. Bagdanov, Joost van de Weijer


  Access Paper or Ask Questions

Visual Transformers with Primal Object Queries for Multi-Label Image Classification


Dec 10, 2021
Vacit Oguz Yazici, Joost van de Weijer, Longlong Yu


  Access Paper or Ask Questions

Hyper-GAN: Transferring Unconditional to Conditional GANs with HyperNetworks


Dec 04, 2021
Héctor Laria, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu

* 14 pages, 12 figures 

  Access Paper or Ask Questions

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition


Nov 11, 2021
Kai Wang, Xialei Liu, Andy Bagdanov, Luis Herranz, Shangling Jui, Joost van de Weijer


  Access Paper or Ask Questions

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification


Oct 22, 2021
Kai Wang, Xialei Liu, Luis Herranz, Joost van de Weijer

* accepted in BMVC 2021 

  Access Paper or Ask Questions

Class-Balanced Active Learning for Image Classification


Oct 09, 2021
Javad Zolfaghari Bengar, Joost van de Weijer, Laura Lopez Fuentes, Bogdan Raducanu

* Accepted at WACV2022 conference 

  Access Paper or Ask Questions

Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation


Oct 08, 2021
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui

* NeurIPS 2021 

  Access Paper or Ask Questions

Reducing Label Effort: Self-Supervised meets Active Learning


Aug 25, 2021
Javad Zolfaghari Bengar, Joost van de Weijer, Bartlomiej Twardowski, Bogdan Raducanu

* Accepted at ICCVW 2021 (Interactive Labeling and Data Augmentation for Vision) 

  Access Paper or Ask Questions

Generalized Source-free Domain Adaptation


Aug 03, 2021
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui

* Accepted by ICCV 2021 

  Access Paper or Ask Questions

When Deep Learners Change Their Mind: Learning Dynamics for Active Learning


Jul 30, 2021
Javad Zolfaghari Bengar, Bogdan Raducanu, Joost van de Weijer

* Accepted in International Conference on Computer Analysis of Images and Patterns (CAIP) 2021 

  Access Paper or Ask Questions

ACAE-REMIND for Online Continual Learning with Compressed Feature Replay


May 18, 2021
Kai Wang, Luis Herranz, Joost van de Weijer

* Under review 

  Access Paper or Ask Questions

TransferI2I: Transfer Learning for Image-to-Image Translation from Small Datasets


May 14, 2021
Yaxing Wang, Hector Laria Mantecon, Joost van de Weijer, Laura Lopez-Fuentes, Bogdan Raducanu

* Technical report 

  Access Paper or Ask Questions

MineGAN++: Mining Generative Models for Efficient Knowledge Transfer to Limited Data Domains


Apr 28, 2021
Yaxing Wang, Abel Gonzalez-Garcia, Chenshen Wu, Luis Herranz, Fahad Shahbaz Khan, Shangling Jui, Joost van de Weijer

* Technical report. arXiv admin note: substantial text overlap with arXiv:1912.05270 

  Access Paper or Ask Questions

Continual learning in cross-modal retrieval


Apr 19, 2021
Kai Wang, Luis Herranz, Joost van de Weijer

* 2nd CLVISION workshop in CVPR 2021 

  Access Paper or Ask Questions

Avalanche: an End-to-End Library for Continual Learning


Apr 01, 2021
Vincenzo Lomonaco, Lorenzo Pellegrini, Andrea Cossu, Antonio Carta, Gabriele Graffieti, Tyler L. Hayes, Matthias De Lange, Marc Masana, Jary Pomponi, Gido van de Ven, Martin Mundt, Qi She, Keiland Cooper, Jeremy Forest, Eden Belouadah, Simone Calderara, German I. Parisi, Fabio Cuzzolin, Andreas Tolias, Simone Scardapane, Luca Antiga, Subutai Amhad, Adrian Popescu, Christopher Kanan, Joost van de Weijer, Tinne Tuytelaars, Davide Bacciu, Davide Maltoni

* Official Website: https://avalanche.continualai.org 

  Access Paper or Ask Questions

On Implicit Attribute Localization for Generalized Zero-Shot Learning


Mar 08, 2021
Shiqi Yang, Kai Wang, Luis Herranz, Joost van de Weijer

* To appear in IEEE Signal Processing Letters. Overlapped with arXiv:2006.05938 

  Access Paper or Ask Questions

Generative Multi-Label Zero-Shot Learning


Jan 28, 2021
Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost van de Weijer

* 10 pages, source code is available at https://github.com/akshitac8/Generative_MLZSL 

  Access Paper or Ask Questions

Self-Training for Class-Incremental Semantic Segmentation


Dec 06, 2020
Lu Yu, Xialei Liu, Joost van de Weijer

* Code will be available 

  Access Paper or Ask Questions

DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs


Nov 11, 2020
Yaxing Wang, Lu Yu, Joost van de Weijer

* NeurIPS2020 

  Access Paper or Ask Questions

Class-incremental learning: survey and performance evaluation


Oct 28, 2020
Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer


  Access Paper or Ask Questions

Unsupervised Domain Adaptation without Source Data by Casting a BAIT


Oct 28, 2020
Shiqi Yang, Yaxing Wang, Joost van de Weijer, Luis Herranz, Shangling Jui


  Access Paper or Ask Questions

Learning to Rank for Active Learning: A Listwise Approach


Jul 31, 2020
Minghan Li, Xialei Liu, Joost van de Weijer, Bogdan Raducanu

* Accepted at ICPR 2020 

  Access Paper or Ask Questions

Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains


Jul 24, 2020
Carola Figueroa-Flores, Bogdan Raducanu, David Berga, Joost van de Weijer


  Access Paper or Ask Questions

RATT: Recurrent Attention to Transient Tasks for Continual Image Captioning


Jul 13, 2020
Riccardo Del Chiaro, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer

* 8 pages, 5 figures, to be published in LifelongML workshop at ICML2020 

  Access Paper or Ask Questions

On Class Orderings for Incremental Learning


Jul 07, 2020
Marc Masana, Bartłomiej Twardowski, Joost van de Weijer

* Accepted at CL-ICML 2020. First two authors contributed equally 

  Access Paper or Ask Questions

Bookworm continual learning: beyond zero-shot learning and continual learning


Jul 06, 2020
Kai Wang, Luis Herranz, Anjan Dutta, Joost van de Weijer


  Access Paper or Ask Questions