Matthijs ：Matthijs is a research scientist at the Facebook AI Research (FAIR) lab in Paris since November 2015. At Facebook he is working on large-scale indexing, machine learning with graphs and similarity search on images and videos. He obtained a PhD at University of Toulouse in 2004. In 2005-2015 he joined the LEAR team at INRIA Grenoble where he worked on a variety of topics, including image indexing, large-scale vector indexing, event recognition in videos and similar video search. In 2010-2015 he developed high-performance geometric algorithms for constructive solid geometry operations. He is interested in snappy algorithms that process images and produce graphical results. Jeff Johnson:Jeff is a research engineer in Facebook AI Research’s SysML (systems for machine learning) research group. He has been at Facebook since January 2013 and is currently based in Los Angeles, California. He works on novel GPU and FPGA/ASIC algorithms for machine learning.
简介：InfoQ中文站秉承“扎根社区、服务社区、引领社区”的理念，旨在通过促进软件开发领域知识与创新的传播。
We present our work on similarity search. We discuss the metrics of this task, and what families of techniques are appropriate to strike several tradeoffs in the space of those metrics. Then we present several recent improvements in this domain, with a particular focus on a machine learning technique that improves the conditioning of the problem. We also introduce the Faiss library that bundles together many of those techniques.
促进软件开发及相关领域知识与创新的传播
京公网安备 11010502039052号
评论