A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/1804.09996v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Link and code: Fast indexing with graphs and compact regression codes
[article]
<span title="2018-04-27">2018</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2018-04-26">2018</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.09996v1">arXiv:1804.09996v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2hwliq3g4bg4zboleuc4pmuwqu">fatcat:2hwliq3g4bg4zboleuc4pmuwqu</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.09996v1">arXiv:1804.09996v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2hwliq3g4bg4zboleuc4pmuwqu">fatcat:2hwliq3g4bg4zboleuc4pmuwqu</a> </span>
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
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.09996v2">arXiv:1804.09996v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/it4fa5sob5a4tfgihaballk5py">fatcat:it4fa5sob5a4tfgihaballk5py</a>
</span>
more »
... 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.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200911234442/https://arxiv.org/pdf/1804.09996v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/73/9c73193b9552c54bf2c63ce4f28f35f58e8f89f4.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1804.09996v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>