Learning a Complete Image Indexing Pipeline

Abstract : To work at scale, a complete image indexing system comprises two components: An inverted file index to restrict the actual search to only a subset that should contain most of the items relevant to the query; An approximate distance computation mechanism to rapidly scan these lists. While supervised deep learning has recently enabled improvements to the latter, the former continues to be based on unsupervised clustering in the literature. In this work, we propose a first system that learns both components within a unifying neural framework of structured binary encoding.
Liste complète des métadonnées

https://hal.inria.fr/hal-01683385
Contributor : Rémi Gribonval <>
Submitted on : Saturday, January 13, 2018 - 2:41:48 PM
Last modification on : Thursday, November 15, 2018 - 11:59:00 AM

Links full text

Identifiers

  • HAL Id : hal-01683385, version 1
  • ARXIV : 1712.04480

Citation

Himalaya Jain, Joaquin Zepeda, Patrick Pérez, Rémi Gribonval. Learning a Complete Image Indexing Pipeline. CVPR 2018 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2018, Salt Lake City, United States. ⟨hal-01683385⟩

Share

Metrics

Record views

939