Corpus ID: 62841605

Spreading vectors for similarity search

@article{Sablayrolles2019SpreadingVF,
  title={Spreading vectors for similarity search},
  author={Alexandre Sablayrolles and M. Douze and C. Schmid and H. J{\'e}gou},
  journal={arXiv: Machine Learning},
  year={2019}
}
  • Alexandre Sablayrolles, M. Douze, +1 author H. Jégou
  • Published 2019
  • Computer Science, Mathematics
  • arXiv: Machine Learning
  • Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. [...] Key Method We propose a new regularizer derived from the Kozachenko--Leonenko differential entropy estimator to enforce uniformity and combine it with a locality-aware triplet loss. Experiments show that our end-to-end approach outperforms most learned quantization methods, and is competitive with the state of the art on widely adopted benchmarks. Furthermore, we show that training without the quantization…Expand Abstract
    Unsupervised Neural Quantization for Compressed-Domain Similarity Search
    2
    Minimizing FLOPs to Learn Efficient Sparse Representations
    Neural Embeddings for Nearest Neighbor Search Under Edit Distance
    2
    Learning to hash with semantic similarity metrics and empirical KL divergence
    NEAREST NEIGHBOR SEARCH
    Learning Space Partitions for Nearest Neighbor Search
    2
    Approximate Nearest Neighbor Search as a Multi-Label Classification Problem.
    Graph-based Nearest Neighbor Search: From Practice to Theory
    3

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 51 REFERENCES
    Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval
    1032
    Cartesian K-Means
    269
    Sparse composite quantization
    66
    SuBiC: A Supervised, Structured Binary Code for Image Search
    51
    Locality sensitive hashing: A comparison of hash function types and querying mechanisms
    243
    Stochastic Neighbor Embedding
    1019
    LSQ++: Lower Running Time and Higher Recall in Multi-codebook Quantization
    9
    In Defense of Product Quantization
    12
    Efficient Indexing of Billion-Scale Datasets of Deep Descriptors
    92