
-
Unsupervised Domain Adaptation without Source Data by Casting a BAIT
Unsupervised domain adaptation (UDA) aims to transfer the knowledge lear...
read it
-
Bookworm continual learning: beyond zero-shot learning and continual learning
We propose bookworm continual learning(BCL), a flexible setting where un...
read it
-
Simple and effective localized attribute representations for zero-shot learning
Zero-shot learning (ZSL) aims to discriminate images from unseen classes...
read it
-
Distributed Learning and Inference with Compressed Images
Modern computer vision requires processing large amounts of data, both w...
read it
-
Generative Feature Replay For Class-Incremental Learning
Humans are capable of learning new tasks without forgetting previous one...
read it
-
Semantic Drift Compensation for Class-Incremental Learning
Class-incremental learning of deep networks sequentially increases the n...
read it
-
Variable Rate Deep Image Compression with Modulated Autoencoder
Variable rate is a requirement for flexible and adaptable image and vide...
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...
read it
-
SDIT: Scalable and Diverse Cross-domain Image Translation
Recently, image-to-image translation research has witnessed remarkable p...
read it
-
Controlling biases and diversity in diverse image-to-image translation
The task of unpaired image-to-image translation is highly challenging du...
read it
-
Multifaceted Analysis of Fine-Tuning in Deep Model for Visual Recognition
In recent years, convolutional neural networks (CNNs) have achieved impr...
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...
read it
-
Cross-Modulation Networks for Few-Shot Learning
A family of recent successful approaches to few-shot learning relies on ...
read it
-
Learning Effective RGB-D Representations for Scene Recognition
Deep convolutional networks (CNN) can achieve impressive results on RGB ...
read it
-
Memory Replay GANs: learning to generate images from new categories without forgetting
Previous works on sequential learning address the problem of forgetting ...
read it
-
LIUM-CVC Submissions for WMT18 Multimodal Translation Task
This paper describes the multimodal Neural Machine Translation systems d...
read it
-
Transferring GANs: generating images from limited data
Transferring the knowledge of pretrained networks to new domains by mean...
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...
read it
-
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
In this paper we propose an approach to avoiding catastrophic forgetting...
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...
read it
-
Scene recognition with CNNs: objects, scales and dataset bias
Since scenes are composed in part of objects, accurate recognition of sc...
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...
read it
-
Domain-adaptive deep network compression
Deep Neural Networks trained on large datasets can be easily transferred...
read it
-
LIUM-CVC Submissions for WMT17 Multimodal Translation Task
This paper describes the monomodal and multimodal Neural Machine Transla...
read it