Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Unsupervised Neural Quantization for Compressed-Domain Similarity Search

About

We tackle the problem of unsupervised visual descriptors compression, which is a key ingredient of large-scale image retrieval systems. While the deep learning machinery has benefited literally all computer vision pipelines, the existing state-of-the-art compression methods employ shallow architectures, and we aim to close this gap by our paper. In more detail, we introduce a DNN architecture for the unsupervised compressed-domain retrieval, based on multi-codebook quantization. The proposed architecture is designed to incorporate both fast data encoding and efficient distances computation via lookup tables. We demonstrate the exceptional advantage of our scheme over existing quantization approaches on several datasets of visual descriptors via outperforming the previous state-of-the-art by a large margin.

Stanislav Morozov, Artem Babenko• 2019

Related benchmarks

TaskDatasetResultRank
Vector QuantizationDeep1M D = 96 (test)
MSE0.06
24
Vector QuantizationBigANN1M D = 128 (test)
MSE0.47
24
Vector QuantizationDeep 1M (test)
MSE0.06
12
Vector QuantizationBigANN 1M (test)
MSE0.47
12
Showing 4 of 4 rows

Other info

Follow for update