Distributed Learning and Inference with Compressed Images

Apr 22, 2020
Sudeep Katakol, Basem Elbarashy, Luis Herranz, Joost van de Weijer, Antonio M. Lopez

* 13 pages, 14 figures 

  Access Model/Code and Paper
Generative Feature Replay For Class-Incremental Learning

Apr 20, 2020
Xialei Liu, Chenshen Wu, Mikel Menta, Luis Herranz, Bogdan Raducanu, Andrew D. Bagdanov, Shangling Jui, Joost van de Weijer

* Accepted at CVPR2020: Workshop on Continual Learning in Computer Vision 

  Access Model/Code and Paper
Semantic Drift Compensation for Class-Incremental Learning

Apr 01, 2020
Lu Yu, Bartłomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost van de Weijer

* Accepted at CVPR2020, Code available at \url{https://github.com/yulu0724/SDC-IL} 

  Access Model/Code and Paper
Variable Rate Deep Image Compression with Modulated Autoencoder

Dec 11, 2019
Fei Yang, Luis Herranz, Joost van de Weijer, José A. Iglesias Guitián, Antonio López, Mikhail Mozerov


  Access Model/Code and Paper
MineGAN: effective knowledge transfer from GANs to target domains with few images

Dec 11, 2019
Yaxing Wang, Abel Gonzalez-Garcia, David Berga, Luis Herranz, Fahad Shahbaz Khan, Joost van de Weijer


  Access Model/Code and Paper
SDIT: Scalable and Diverse Cross-domain Image Translation

Aug 19, 2019
Yaxing Wang, Abel Gonzalez-Garcia, Joost van de Weijer, Luis Herranz

* ACM-MM2019 camera ready 

  Access Model/Code and Paper
Controlling biases and diversity in diverse image-to-image translation

Jul 23, 2019
Yaxing Wang, Abel Gonzalez-Garcia, Joost van de Weijer, Luis Herranz

* The paper is under consideration at Computer Vision and Image Understanding 

  Access Model/Code and Paper
Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition

Jul 11, 2019
Xiangyang Li, Luis Herranz, Shuqiang Jiang

* Accepted by ACM Transactions on Data Science 

  Access Model/Code and Paper
Mix and match networks: multi-domain alignment for unpaired image-to-image translation

Mar 08, 2019
Yaxing Wang, Luis Herranz, Joost van de Weijer

* overlap the previous version. arXiv admin note: text overlap with arXiv:1804.02199 

  Access Model/Code and Paper
Cross-Modulation Networks for Few-Shot Learning

Dec 01, 2018
Hugo Prol, Vincent Dumoulin, Luis Herranz

* Accepted at NIPS 2018 Workshop on Meta-Learning. Source code available at https://github.com/hprop/cross-modulation-nets 

  Access Model/Code and Paper
Memory Replay GANs: learning to generate images from new categories without forgetting

Oct 29, 2018
Chenshen Wu, Luis Herranz, Xialei Liu, Yaxing Wang, Joost van de Weijer, Bogdan Raducanu

* Appear in NIPS 2018 

  Access Model/Code and Paper
Transferring GANs: generating images from limited data

Oct 02, 2018
Yaxing Wang, Chenshen Wu, Luis Herranz, Joost van de Weijer, Abel Gonzalez-Garcia, Bogdan Raducanu

* ECCV2018-camera ready 

  Access Model/Code and Paper
Learning Effective RGB-D Representations for Scene Recognition

Sep 17, 2018
Xinhang Song, Shuqiang Jiang, Luis Herranz, Chengpeng Chen

* IEEE Transactions on Image Processing, vol. 28, no. 2, pp. 980-993, Feb. 2019 
* Accepted at IEEE Transactions on Image Processing 

  Access Model/Code and Paper
LIUM-CVC Submissions for WMT18 Multimodal Translation Task

Sep 01, 2018
Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, Marc Masana, Luis Herranz, Joost van de Weijer

* WMT2018 

  Access Model/Code and Paper
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

Jul 12, 2018
Xialei Liu, Marc Masana, Luis Herranz, Joost Van de Weijer, Antonio M. Lopez, Andrew D. Bagdanov

* Accepted at ICPR'18. First two authors contributed equally 

  Access Model/Code and Paper
Mix and match networks: encoder-decoder alignment for zero-pair image translation

Apr 06, 2018
Yaxing Wang, Joost van de Weijer, Luis Herranz

* Accepted CVPR 2018 

  Access Model/Code and Paper
Food recognition and recipe analysis: integrating visual content, context and external knowledge

Jan 22, 2018
Luis Herranz, Weiqing Min, Shuqiang Jiang

* Survey about contextual food recognition and multimodal recipe analysis 

  Access Model/Code and Paper
Scene recognition with CNNs: objects, scales and dataset bias

Jan 21, 2018
Luis Herranz, Shuqiang Jiang, Xiangyang Li

* L. Herranz, S. Jiang, X. Li, "Scene recognition with CNNs: objects, scales and dataset bias", Proc. International Conference on Computer Vision and Pattern Recognition (CVPR16), Las Vegas, Nevada, USA, June 2016 
* CVPR 2016 

  Access Model/Code and Paper
Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

Jan 21, 2018
Xinhang Song, Luis Herranz, Shuqiang Jiang

* AAAI Conference on Artificial Intelligence 2017, 4271-4277 
* AAAI Conference on Artificial Intelligence 2017 

  Access Model/Code and Paper
Domain-adaptive deep network compression

Sep 06, 2017
Marc Masana, Joost van de Weijer, Luis Herranz, Andrew D. Bagdanov, Jose M Alvarez

* Accepted at ICCV 2017 

  Access Model/Code and Paper
LIUM-CVC Submissions for WMT17 Multimodal Translation Task

Jul 14, 2017
Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz, Joost van de Weijer

* MMT System Description Paper for WMT17 

  Access Model/Code and Paper