Efficient large-scale approximate nearest neighbor search on the gpu
P Wieschollek, O Wang… - Proceedings of the …, 2016 - openaccess.thecvf.com
We present a new approach for efficient approximate nearest neighbor (ANN) search in high
dimensional spaces, extending the idea of Product Quantization. We propose a two level …
dimensional spaces, extending the idea of Product Quantization. We propose a two level …
Ggnn: Graph-based gpu nearest neighbor search
F Groh, L Ruppert, P Wieschollek… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Approximate nearest neighbor (ANN) search in high dimensions is an integral part of
several computer vision systems and gains importance in deep learning with explicit …
several computer vision systems and gains importance in deep learning with explicit …
Finding the number of clusters using a small training sequence
DS Kim - IEEE Access, 2023 - ieeexplore.ieee.org
In clustering the training sequence (TS), K-means algorithm tries to find empirically optimal
representative vectors that achieve the empirical minimum to inductively design optimal …
representative vectors that achieve the empirical minimum to inductively design optimal …
Robustiq: A robust ann search method for billion-scale similarity search on gpus
GPU-based methods represent state-of-the-art in approximate nearest neighbor (ANN)
search, as they are scalable (billion-scale), accurate (high recall) as well as efficient (sub …
search, as they are scalable (billion-scale), accurate (high recall) as well as efficient (sub …
Upper bounds on empirically optimal quantizers
In designing a vector quantizer using a training sequence (TS), the training algorithm tries to
find an empirically optimal quantizer that minimizes the selected distortion criteria using the …
find an empirically optimal quantizer that minimizes the selected distortion criteria using the …
Sample-adaptive product quantization: Asymptotic analysis and examples
Vector quantization (VQ) is an efficient data compression technique for low bit rate
applications. However the major disadvantage of VQ is that its encoding complexity …
applications. However the major disadvantage of VQ is that its encoding complexity …
Design of sample adaptive product quantizers for noisy channels
Channel-optimized vector quantization (COVQ) has proven to be an effective joint source-
channel coding technique that makes the underlying quantizer robust to channel noise …
channel coding technique that makes the underlying quantizer robust to channel noise …
Training ratio and comparison of trained vector quantizers
DS Kim - IEEE transactions on signal processing, 2003 - ieeexplore.ieee.org
The vector quantizer (VQ) codebook is usually designed by clustering a training sequence
(TS) drawn from the underlying distribution function. In order to cluster a TS, we may use the …
(TS) drawn from the underlying distribution function. In order to cluster a TS, we may use the …
Noisy source vector quantization using kernel regression
YA Ghassabeh, F Rudzicz - IEEE Transactions on …, 2014 - ieeexplore.ieee.org
The problem of designing an optimal vector quantizer when there is access to the noise-free
source has been well studied over the past five decades. However, in many real-world …
source has been well studied over the past five decades. However, in many real-world …
Vector quantization by companding a union of Z-lattices
TZ Shabestary, P Hedelin - IEEE transactions on information …, 2005 - ieeexplore.ieee.org
An encoding scheme is presented based on random coding theory in conjunction with
companding techniques. This combination provides an easy design, and a low-storage …
companding techniques. This combination provides an easy design, and a low-storage …