Co-occurrence of deep convolutional features for image search

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-occurr...

Descripción completa

Detalles Bibliográficos
Autores: Forcén Carvalho, Juan Ignacio, Pagola Barrio, Miguel, Barrenechea Tartas, Edurne, Bustince Sola, Humberto
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2020
País:España
Institución:Universidad Pública de Navarra
Repositorio:Academica-e. Repositorio Institucional de la Universidad Pública de Navarra
OAI Identifier:oai:academica-e.unavarra.es:2454/39071
Acceso en línea:https://hdl.handle.net/2454/39071
Access Level:acceso abierto
Palabra clave:Co-occurrence
Image retrieval
Feature aggregation
Pooling
Descripción
Sumario: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.