Nearest Neighbors Using Compact Sparse Codes - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2014

Nearest Neighbors Using Compact Sparse Codes


In this paper, we propose a novel scheme for approximate nearest neighbor (ANN) retrieval based on dictionary learning and sparse coding. Our key innovation is to build compact codes, dubbed SpANN codes, using the active set of sparse coded data. These codes are then used to index an inverted file table for fast retrieval. The active sets are often found to be sensitive to small differences among data points, resulting in only near duplicate retrieval. We show that this sensitivity is related to the coherence of the dictionary; small coherence resulting in better retrieval. To this end, we propose a novel dictionary learning formulation with incoherence constraints and an efficient method to solve it. Experiments are conducted on two state-of-the-art computer vision datasets with 1M data points and show an order of magnitude improvement in retrieval accuracy without sacrificing memory and query time compared to the state-of-the-art methods.
Fichier principal
Vignette du fichier
spannicml2014.pdf (306.16 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01057690 , version 1 (03-12-2014)


  • HAL Id : hal-01057690 , version 1


Anoop Cherian. Nearest Neighbors Using Compact Sparse Codes. ICML - 31st International Conference on Machine Learning, Jun 2014, Beijing, China. pp.1053-1061. ⟨hal-01057690⟩
349 View
603 Download


Gmail Facebook X LinkedIn More