Luis Herranz

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

We propose bookworm continual learning(BCL), a flexible setting where un...
06/26/2020 ∙ by Kai Wang, et al. ∙ 0 ∙ share

read it
Simple and effective localized attribute representations for zero-shot learning

Zero-shot learning (ZSL) aims to discriminate images from unseen classes...
06/10/2020 ∙ by Shiqi Yang, et al. ∙ 15 ∙ share

read it
Distributed Learning and Inference with Compressed Images

Modern computer vision requires processing large amounts of data, both w...
04/22/2020 ∙ by Sudeep Katakol, et al. ∙ 1 ∙ share

read it
Generative Feature Replay For Class-Incremental Learning

Humans are capable of learning new tasks without forgetting previous one...
04/20/2020 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

read it
Semantic Drift Compensation for Class-Incremental Learning

Class-incremental learning of deep networks sequentially increases the n...
04/01/2020 ∙ by Lu Yu, et al. ∙ 0 ∙ share

read it
Variable Rate Deep Image Compression with Modulated Autoencoder

Variable rate is a requirement for flexible and adaptable image and vide...
12/11/2019 ∙ by Fei Yang, et al. ∙ 0 ∙ share

read it
MineGAN: effective knowledge transfer from GANs to target domains with few images

One of the attractive characteristics of deep neural networks is their a...
12/11/2019 ∙ by Yaxing Wang, et al. ∙ 40 ∙ share

read it
SDIT: Scalable and Diverse Cross-domain Image Translation

Recently, image-to-image translation research has witnessed remarkable p...
08/19/2019 ∙ by Yaxing Wang, et al. ∙ 5 ∙ share

read it
Controlling biases and diversity in diverse image-to-image translation

The task of unpaired image-to-image translation is highly challenging du...
07/23/2019 ∙ by Yaxing Wang, et al. ∙ 7 ∙ share

read it
Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition

In recent years, convolutional neural networks (CNNs) have achieved impr...
07/11/2019 ∙ by Xiangyang Li, et al. ∙ 6 ∙ share

read it
Mix and match networks: multi-domain alignment for unpaired image-to-image translation

This paper addresses the problem of inferring unseen cross-domain and cr...
03/08/2019 ∙ by Yaxing Wang, et al. ∙ 8 ∙ share

read it
Cross-Modulation Networks for Few-Shot Learning

A family of recent successful approaches to few-shot learning relies on ...
12/01/2018 ∙ by Hugo Prol, et al. ∙ 0 ∙ share

read it
Learning Effective RGB-D Representations for Scene Recognition

Deep convolutional networks (CNN) can achieve impressive results on RGB ...
09/17/2018 ∙ by Xinhang Song, et al. ∙ 8 ∙ share

read it
Memory Replay GANs: learning to generate images from new categories without forgetting

Previous works on sequential learning address the problem of forgetting ...
09/06/2018 ∙ by Chenshen Wu, et al. ∙ 12 ∙ share

read it
LIUM-CVC Submissions for WMT18 Multimodal Translation Task

This paper describes the multimodal Neural Machine Translation systems d...
09/01/2018 ∙ by Ozan Caglayan, et al. ∙ 0 ∙ share

read it
Transferring GANs: generating images from limited data

Transferring the knowledge of pretrained networks to new domains by mean...
05/04/2018 ∙ by Yaxing Wang, et al. ∙ 0 ∙ share

read it
Mix and match networks: encoder-decoder alignment for zero-pair image translation

We address the problem of image translation between domains or modalitie...
04/06/2018 ∙ by Yaxing Wang, et al. ∙ 0 ∙ share

read it
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

In this paper we propose an approach to avoiding catastrophic forgetting...
02/08/2018 ∙ by Xialei Liu, et al. ∙ 0 ∙ share

read it
Food recognition and recipe analysis: integrating visual content, context and external knowledge

The central role of food in our individual and social life, combined wit...
01/22/2018 ∙ by Luis Herranz, et al. ∙ 0 ∙ share

read it
Scene recognition with CNNs: objects, scales and dataset bias

Since scenes are composed in part of objects, accurate recognition of sc...
01/21/2018 ∙ by Luis Herranz, et al. ∙ 0 ∙ share

read it
Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

Scene recognition with RGB images has been extensively studied and has r...
01/21/2018 ∙ by Xinhang Song, et al. ∙ 0 ∙ share

read it
Domain-adaptive deep network compression

Deep Neural Networks trained on large datasets can be easily transferred...
09/04/2017 ∙ by Marc Masana, et al. ∙ 0 ∙ share

read it
LIUM-CVC Submissions for WMT17 Multimodal Translation Task

This paper describes the monomodal and multimodal Neural Machine Transla...
07/14/2017 ∙ by Ozan Caglayan, et al. ∙ 0 ∙ share

read it

Luis Herranz

Featured Co-authors

Fahad Shahbaz Khan

Joost van de Weijer

Kai Wang

Antonio M. Lopez

Jose M. Alvarez

Loïc Barrault

Abel Gonzalez-Garcia

Vincent Dumoulin

Ozan Caglayan

Fethi Bougares

Yaxing Wang

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

Simple and effective localized attribute representations for zero-shot learning

Distributed Learning and Inference with Compressed Images

Generative Feature Replay For Class-Incremental Learning

Semantic Drift Compensation for Class-Incremental Learning

Variable Rate Deep Image Compression with Modulated Autoencoder

MineGAN: effective knowledge transfer from GANs to target domains with few images

SDIT: Scalable and Diverse Cross-domain Image Translation

Controlling biases and diversity in diverse image-to-image translation

Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition

Mix and match networks: multi-domain alignment for unpaired image-to-image translation

Cross-Modulation Networks for Few-Shot Learning

Learning Effective RGB-D Representations for Scene Recognition

Memory Replay GANs: learning to generate images from new categories without forgetting

LIUM-CVC Submissions for WMT18 Multimodal Translation Task

Transferring GANs: generating images from limited data

Mix and match networks: encoder-decoder alignment for zero-pair image translation

Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting

Food recognition and recipe analysis: integrating visual content, context and external knowledge

Scene recognition with CNNs: objects, scales and dataset bias

Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs

Domain-adaptive deep network compression

LIUM-CVC Submissions for WMT17 Multimodal Translation Task