Link and code: Fast indexing with graphs and compact regression codes

Abstract : Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements. In this paper, we revisit these approaches by considering, additionally, the memory constraint required to index billions of images on a single server. This leads us to propose a method based both on graph traversal and compact representations. We encode the indexed vectors using quantization and exploit the graph structure to refine the similarity estimation. In essence, our method takes the best of these two worlds: the search strategy is based on nested graphs, thereby providing high precision with a relatively small set of comparisons. At the same time it offers a significant memory compression. As a result, our approach outperforms the state of the art on operating points considering 64–128 bytes per vector, as demonstrated by our results on two billion-scale public benchmarks.
Complete list of metadatas

Cited literature [24 references]  Display  Hide  Download

https://hal.inria.fr/hal-01955971
Contributor : Alexandre Sablayrolles <>
Submitted on : Friday, December 14, 2018 - 5:14:52 PM
Last modification on : Sunday, March 10, 2019 - 4:40:35 PM
Long-term archiving on : Friday, March 15, 2019 - 4:50:34 PM

File

1804.09996.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou. Link and code: Fast indexing with graphs and compact regression codes. CVPR 2018 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2018, Salt Lake City, United States. pp.3646-3654, ⟨10.1109/CVPR.2018.00384⟩. ⟨hal-01955971⟩

Share

Metrics

Record views

252

Files downloads

141