Document - Efficient indexing of regional maximum activations of convolutions using full-text search engines

2017

Conference article Open Access

Efficient indexing of regional maximum activations of convolutions using full-text search engines

Amato G., Carrara F., Falchi F., Gennaro C.

Permutation-Based Indexing Similarity Search Deep Convolutional Neural Network

In this paper, we adapt a surrogate text representation technique to develop efficient instance-level image retrieval using Regional Maximum Activations of Convolutions (R-MAC). R-MAC features have recently showed outstanding performance in visual instance retrieval. However, contrary to the activations of hidden layers adopting ReLU (Rectified Linear Unit), these features are dense. This constitutes an obstacle to the direct use of inverted indexes, which rely on sparsity of data. We propose the use of deep permutations, a recent approach for efficient evaluation of permutations, to generate surrogate text representation of R-MAC features, enabling indexing of visual features as text into a standard search-engine. The experiments, conducted on Lucene, show the effectiveness and efficiency of the proposed approach.

Source: 2017 ACM on International Conference on Multimedia Retrieval (ICMR 2017), pp. 420–423, Bucharest, Romania, 6-9 June 2017

Publisher: ACM Press, New York, USA

Metrics

Back to previous page

Cite as

BibTeX entry

@inproceedings{oai:it.cnr:prodotti:384737,
	title = {Efficient indexing of regional maximum activations of convolutions using full-text search engines},
	author = {Amato G. and Carrara F. and Falchi F. and Gennaro C.},
	publisher = {ACM Press, New York, USA},
	doi = {10.1145/3078971.3079035},
	booktitle = {2017 ACM on International Conference on Multimedia Retrieval (ICMR 2017), pp. 420–423, Bucharest, Romania, 6-9 June 2017},
	year = {2017}
}