Name
Title | ||
|---|---|---|
Efficient Indexing of Regional Maximum Activations of Convolutions using Full-Text Search Engines. |
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1145/3078971.3079035 | ICMR |
Keywords | Field | DocType |
Similarity Search, Permutation-Based Indexing, Deep Convolutional Neural Network | Data mining,Rectifier (neural networks),Computer science,Image retrieval,Search engine indexing,Artificial intelligence,Nearest neighbor search,Obstacle,Pattern recognition,Convolution,Full text search,Permutation,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.36 | 24 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Giuseppe Amato | 1 | 505 | 106.68 |
| Fabio Carrara | 2 | 29 | 8.17 |
| Fabrizio Falchi | 3 | 459 | 55.65 |
| Claudio Gennaro | 4 | 490 | 57.23 |