Efficient Image Search with Neural Net Features

Logo poskytovatele

Varování

Publikace nespadá pod Filozofickou fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

NOVÁK David ČECH Jan ZEZULA Pavel

Rok publikování 2015
Druh Článek ve sborníku
Konference Similarity Search and Applications: 8th International Conference, SISAP 2015, Glasgow, UK, October 12-14, 2015, Proceedings
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www DOI link
Doi http://dx.doi.org/10.1007/978-3-319-25087-8_22
Obor Informatika
Klíčová slova metric indexing; deep convolutional neural network; contentbased image retrieval
Popis We present an efficiency evaluation of similarity search techniques applied on visual features from deep neural networks. Our test collection consists of 20 million 4096-dimensional descriptors (320GB of data). We test approximate k-NN search using several techniques, specifically FLANN library (a popular in-memory implementation of k-d tree forest), M-Index (that uses recursive Voronoi partitioning of a metric space), and PPP-Codes, which work with memory codes of metric objects and use disk storage for candidate refinement. Our evaluation shows that as long as the data fit in main memory, the FLANN and the M-Index have practically the same ratio between precision and response time. The PPP-Codes identify candidate sets ten times smaller then the other techniques and the response times are around 500 ms for the whole 20M dataset stored on the disk. The visual search with this index is available as an online demo application. The collection of 20M descriptors is provided as a public dataset to academic community.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.