Publication: Co-occurrence of deep convolutional features for image search
Date
Director
Publisher
Project identifier
Abstract
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.
Description
Keywords
Department
Faculty/School
Degree
Doctorate program
item.page.cita
item.page.rights
© 2020 Elsevier B.V. This manuscript version is made available under the CC-BY-NC-ND 4.0.
Los documentos de Academica-e están protegidos por derechos de autor con todos los derechos reservados, a no ser que se indique lo contrario.