Search Results for author: Jesus Labarta

Found 5 papers, 0 papers with code

Feature discriminativity estimation in CNNs for transfer learning

no code implementations8 Nov 2019 Victor Gimenez-Abalos, Armand Vilalta, Dario Garcia-Gasulla, Jesus Labarta, Eduard Ayguadé

The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem.

Transfer Learning

A Visual Distance for WordNet

no code implementations24 Apr 2018 Raquel Pérez-Arnal, Armand Vilalta, Dario Garcia-Gasulla, Ulises Cortés, Eduard Ayguadé, Jesus Labarta

WordNet, which includes a wide variety of concepts associated with words (i. e., synsets), is often used as a source for computing those distances.

Full-Network Embedding in a Multimodal Embedding Pipeline

no code implementations WS 2017 Armand Vilalta, Dario Garcia-Gasulla, Ferran Parés, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

In this paper we evaluate the impact of using the Full-Network embedding in this setting, replacing the original image representation in a competitive multimodal embedding generation scheme.

Image Retrieval Network Embedding

Building Graph Representations of Deep Vector Embeddings

no code implementations WS 2017 Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes.

Graph Embedding

An Out-of-the-box Full-network Embedding for Convolutional Neural Networks

no code implementations ICLR 2018 Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training is not an option.

General Classification Image Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.