Vector and line quantization for billion-scale similarity search on GPUs

Billion-scale similarity search with GPUs

Similarity search finds application in specialized database systems handling complex data such as images or videos, which are typically represented by high-dimensional features and require specific indexing structures. This paper tackles the problem of better utilizing GPUs for this task. While GPUs excel at data-parallel tasks, prior approaches are bottlenecked by algorithms that expose less p...

Adaptable Similarity Search Using Vector Quantization

Adaptable similarity queries based on quadratic form distance functions are widely popular in data mining applications, particularly for domains such as multimedia, CAD, molecular biology or medical image databases. Recently it has been recognized that quantization of feature vectors can substantially improve query processing for Euclidean distance functions, as demonstrated by the scan-based V...

Statistical quantization for similarity search

Multiscale Quantization for Fast Similarity Search

We propose a multiscale quantization approach for fast similarity search on large, high-dimensional datasets. The key insight of the approach is that quantization methods, in particular product quantization, perform poorly when there is large variance in the norms of the data points. This is a common scenario for realworld datasets, especially when doing product quantization of residuals obtain...

Efficient Similarity Search on Vector Sets

Similarity search in database systems is becoming an increasingly important task in modern application domains such as multimedia, molecular biology, medical imaging, computer aided design and many others. Whereas most of the existing similarity models are based on feature vectors, there exist some models which use very complex object representations such as trees and graphs. A promising way be...