Exponential family Fisher vector for image classification

One of the fundamental problems in image classification is to devise models that allow us to relate the images to higher-level semantic concepts in an efficient and reliable way. A widely used approach consists on extracting local descriptors from the images and to summarize them into an image-level...

Descripción completa

Detalles Bibliográficos
Autores principales: Sánchez, Jorge, Redolfi, Javier
Formato: Artículo draft
Lenguaje:Inglés
Inglés
Publicado: 2019
Materias:
image classification
Fisher kernel
Fisher vectors
exponential family
Acceso en línea:http://hdl.handle.net/20.500.12272/3972
https://doi.org/10.1016/j.patrec.2015.03.010
Aporte de:
RIA - Repositorio Institucional Abierto (UTN) de Universidad Tecnológica Nacional
id I68-R174-20.500.12272-3972
record_format dspace
institution Universidad Tecnológica Nacional
institution_str I-68
repository_str R-174
collection RIA - Repositorio Institucional Abierto (UTN)
language Inglés
Inglés
topic image classification
Fisher kernel
Fisher vectors
exponential family
spellingShingle image classification
Fisher kernel
Fisher vectors
exponential family
Sánchez, Jorge
Redolfi, Javier
Exponential family Fisher vector for image classification
topic_facet image classification
Fisher kernel
Fisher vectors
exponential family
description One of the fundamental problems in image classification is to devise models that allow us to relate the images to higher-level semantic concepts in an efficient and reliable way. A widely used approach consists on extracting local descriptors from the images and to summarize them into an image-level representation. Within this framework, the Fisher vector (FV) is one of the most robust signatures to date. In the FV, local descriptors are modeled as samples drawn from a mixture of Gaussian pdfs. An image is represented by a gradient vector characterizing the distributions of samples w.r.t. the model. Equipped with robust features like SIFT, the FV has shown state-of-the-art performance on different recognition problems. However, it is not clear how it should be applied when the feature space is clearly non-Euclidean, leading to heuristics that ignore the underlying structure of the space. In this paper we generalize the Gaussian FV to a broader family of distributions known as the exponential family. The model, termed exponential family Fisher vectors (eFV), provides a unified framework from which rich and powerful representations can be derived. Experimental results show the generality and flexibility of our approach.
format Artículo
draft
Artículo
author Sánchez, Jorge
Redolfi, Javier
author_facet Sánchez, Jorge
Redolfi, Javier
author_sort Sánchez, Jorge
title Exponential family Fisher vector for image classification
title_short Exponential family Fisher vector for image classification
title_full Exponential family Fisher vector for image classification
title_fullStr Exponential family Fisher vector for image classification
title_full_unstemmed Exponential family Fisher vector for image classification
title_sort exponential family fisher vector for image classification
publishDate 2019
url http://hdl.handle.net/20.500.12272/3972
https://doi.org/10.1016/j.patrec.2015.03.010
work_keys_str_mv AT sanchezjorge exponentialfamilyfishervectorforimageclassification
AT redolfijavier exponentialfamilyfishervectorforimageclassification
bdutipo_str Repositorios
_version_ 1764820552458960900

Ejemplares similares