The activation of the Deep Convolutional Neural Networks hidden layers can be successfully used as features, often referred as Deep Features, in generic visual similarity search tasks. Recently scientists have shown that permutation-based methods o ffer very good performance in indexing and supporting approximate similarity search on large database of objects. Permutation-based approaches represent metric objects as sequences (permutations) of reference objects,
chosen from a predefi ned set of data. However, associating objects with permutations might have a high cost due to the distance calculation between the data objects and the reference objects. In this work, we propose a new approach to generate permutations at a very low computational cost, when objects to be indexed are Deep Features. We show that the permutations generated using the proposed method are more eff ective than those obtained using pivot selection criteria speci fically developed for permutation-based methods.
Keywords: {Similarity Search, Permutation-Based Indexing, Deep Convolutional Neural Network}
File: http://link.springer.com/chapter/10.1007/978-3-319-46759-7_7
