Joint Learning of Deep Retrieval Model and Product Quantization based Embedding Index

05/09/2021
by   Han Zhang, et al.
1

Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems. Traditional approaches, often separating the two steps of embedding learning and index building, incur additional indexing time and decayed retrieval accuracy. In this paper, we propose a novel method called Poeem, which stands for product quantization based embedding index jointly trained with deep retrieval model, to unify the two separate steps within an end-to-end training, by utilizing a few techniques including the gradient straight-through estimator, warm start strategy, optimal space decomposition and Givens rotation. Extensive experimental results show that the proposed method not only improves retrieval accuracy significantly but also reduces the indexing time to almost none. We have open sourced our approach for the sake of comparison and reproducibility.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/15/2016

Scalable Image Retrieval by Sparse Product Quantization

Fast Approximate Nearest Neighbor (ANN) search technique for high-dimens...
research
03/09/2022

Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes

Product quantization (PQ) coupled with a space rotation, is widely used ...
research
11/19/2018

End-to-End Retrieval in Continuous Space

Most text-based information retrieval (IR) systems index objects by word...
research
04/14/2022

Composite Code Sparse Autoencoders for first stage retrieval

We propose a Composite Code Sparse Autoencoder (CCSA) approach for Appro...
research
10/05/2022

Active Image Indexing

Image copy detection and retrieval from large databases leverage two com...
research
08/02/2021

Jointly Optimizing Query Encoder and Product Quantization to Improve Retrieval Performance

Recently, Information Retrieval community has witnessed fast-paced advan...
research
06/15/2018

Efficient Nearest Neighbors Search for Large-Scale Landmark Recognition

The problem of landmark recognition has achieved excellent results in sm...

Please sign up or login with your details

Forgot password? Click here to reset