Pith. sign in

REVIEW

Polysemous codes

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1609.01882 v2 pith:Q7KTLZK3 submitted 2016-09-07 cs.CV cs.DBcs.ITcs.LGmath.IT

Polysemous codes

classification cs.CV cs.DBcs.ITcs.LGmath.IT
keywords distancecodessearchvectorsapproximatehammingpolysemousaccelerates
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This paper considers the problem of approximate nearest neighbor search in the compressed domain. We introduce polysemous codes, which offer both the distance estimation quality of product quantization and the efficient comparison of binary codes with Hamming distance. Their design is inspired by algorithms introduced in the 90's to construct channel-optimized vector quantizers. At search time, this dual interpretation accelerates the search. Most of the indexed vectors are filtered out with Hamming distance, letting only a fraction of the vectors to be ranked with an asymmetric distance estimator. The method is complementary with a coarse partitioning of the feature space such as the inverted multi-index. This is shown by our experiments performed on several public benchmarks such as the BIGANN dataset comprising one billion vectors, for which we report state-of-the-art results for query times below 0.3\,millisecond per core. Last but not least, our approach allows the approximate computation of the k-NN graph associated with the Yahoo Flickr Creative Commons 100M, described by CNN image descriptors, in less than 8 hours on a single machine.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.