Co-occurrence of deep convolutional features for image search
Fecha
2020Autor
Versión
Acceso abierto / Sarbide irekia
Tipo
Artículo / Artikulua
Versión
Versión aceptada / Onetsi den bertsioa
Impacto
|
10.1016/j.imavis.2020.103909
Resumen
Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last co ...
[++]
Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last convolutional layer. Combining this co-occurrence map with the feature map, we achieve an improved image representation. We present two different methods to get the co-occurrence representation, the first one based on direct aggregation of activations, and the second one, based on a trainable co-occurrence representation. The image descriptors derived from our methodology improve the performance in very well-known image retrieval datasets as we prove in the experiments. [--]
Materias
Co-occurrence,
Image retrieval,
Feature aggregation,
Pooling
Editor
Elsevier
Publicado en
Image and Vision Computing, 2020, 97, 103909
Departamento
Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas /
Universidad Pública de Navarra/Nafarroako Unibertsitate Publikoa. Institute of Smart Cities - ISC /
Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematika Saila