Spreading vectors for similarity search

@inproceedings{Sablayrolles2018SpreadingVF,
  title={Spreading vectors for similarity search},
  author={Alexandre Sablayrolles and Matthijs Douze and Cordelia Schmid and Herv{\'e} J{\'e}gou},
  booktitle={ICLR},
  year={2018}
}
Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for optimal performance, thus adapting quantizers to the data. In this work, we propose to reverse this paradigm and adapt the data to the quantizer: we train a neural net which last layer forms a fixed parameter-free quantizer, such as pre-defined points of a hyper-sphere. As a proxy objective, we design and train a… CONTINUE READING
17
Twitter Mentions

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 47 REFERENCES

Optimized Product Quantization for Approximate Nearest Neighbor Search

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Learning Fine-Grained Image Similarity with Deep Ranking

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Product Quantization for Nearest Neighbor Search

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2011
VIEW 8 EXCERPTS

Searching in one billion vectors: Re-rank with source coding

  • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2011
VIEW 8 EXCERPTS