Online Nearest Neighbor Search in Binary Space

Eghbali, Sepehr; Ashtiani, Hassan; Tahvildari, Ladan

doi:10.1109/icdm.2017.104

Cited by 8 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Embedding to the Hamming space is often used in similarity search to reduce the volume of processed data and to speed up query processing [14], [1], [6]. The speed up is also enabled by the efficiency of Hamming distance evaluation, but the sequential evaluation of all distances h(q, o), o ∈ X is not efficient enough for many applications [9], [10]. Indexing of the Hamming space is difficult due to the dimensionality curse which says that efficiency of indexes degrades towards sequential scan with increasing data complexity [11], [12].…”

Section: A Related Workmentioning

confidence: 99%

“…The Hamming Weight Tree (HWT) [10] have been proposed to efficiently evaluate similarity queries in the Hamming space. It utilises the L 1 norm of bit string o, i.e.…”

Section: Hamming Weight Treementioning

confidence: 99%

“…Hamming space (domain and Hamming distance) λ length of bit strings X, X ⊆ S λ dataset and its transformation q, k query bit strings, number of objects to be found o = (0, 1) bit string o with two bits 0 and 1 w [10] propose to split nodes of the HWT that contain more than t bit strings for some selected threshold t. In general, nodes in level l consider bit strings split into 2 l−1 parts and weights are then evaluated on these disjunctive parts. Let us denote o[a.…”

Section: Hamming Weight Treementioning

confidence: 99%

“…We measure the efficiency of the HWT precise similarity search regarding search time (in seconds). Our implementation is based on the C++ code used in [10]. We evaluate 1,000 1NN queries on each configuration, and we present average values.…”

Section: Experiments -Efficiency Of the Hwtmentioning

confidence: 99%

“…Recently, authors of the Hamming weight tree (HWT) proposed to lower bound the Hamming distance using the number of 1s in the bit strings and to use this lower bound to prune the Hamming search space during evaluation of similarity queries [10]. The efficiency of query evaluations depends on the tightness of the provided lower bounds.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Modifying Hamming Spaces for Efficient Search

Mic

Novák

Zezula

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

We focus on the efficient search for the most similar bit strings to a given query in the Hamming space. The Hamming distance can be lower-bounded by the difference of the "number of ones" in the compared strings, i.e. of their weights. Recently, such property has been successfully used by the Hamming Weight Tree (HWT) indexing structure. We propose modifications of the bit strings that preserve pairwise Hamming distances but improve the tightness of these lower bounds, so the query evaluation with the HWT is several times faster. We also show that the unbalanced bit strings, recently reported to provide similar quality of search as the traditionally used balanced bit strings, can be more efficiently indexed with the HWT. Combined with the distance preserving modifications, the HWT query evaluation can be more than one order of magnitude faster than the HWT baseline. Keywords-Similarity search, Hamming space, HammingWeight Tree, Lower bound in the Hamming space 1 i.e. bit strings with bits set to 1 in a different ratio then a half of bit strings o ∈ X

show abstract

Section: A Related Workmentioning

confidence: 99%

“…The Hamming Weight Tree (HWT) [10] have been proposed to efficiently evaluate similarity queries in the Hamming space. It utilises the L 1 norm of bit string o, i.e.…”

Section: Hamming Weight Treementioning

confidence: 99%

Section: Hamming Weight Treementioning

confidence: 99%

Section: Experiments -Efficiency Of the Hwtmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Modifying Hamming Spaces for Efficient Search

Mic

Novák

Zezula

2018

2018 IEEE International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

show abstract

Efficient Testing of Physically Unclonable Functions for Uniqueness

Araújo

Patil

Marzulo

et al. 2019

2019 IEEE 28th Asian Test Symposium (ATS)

View full text Add to dashboard Cite

Deep Spherical Quantization for Image Search

Eghbali

Tahvildari

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

View full text Add to dashboard Cite

Hashing methods, which encode high-dimensional images with compact discrete codes, have been widely applied to enhance large-scale image retrieval. In this paper, we put forward Deep Spherical Quantization (DSQ), a novel method to make deep convolutional neural networks generate supervised and compact binary codes for efficient image search. Our approach simultaneously learns a mapping that transforms the input images into a low-dimensional discriminative space, and quantizes the transformed data points using multi-codebook quantization. To eliminate the negative effect of norm variance on codebook learning, we force the network to L 2 normalize the extracted features and then quantize the resulting vectors using a new supervised quantization technique specifically designed for points lying on a unit hypersphere. Furthermore, we introduce an easyto-implement extension of our quantization technique that enforces sparsity on the codebooks. Extensive experiments demonstrate that DSQ and its sparse variant can generate semantically separable compact binary codes outperforming many state-of-the-art image retrieval methods on three benchmarks.

show abstract

Online Nearest Neighbor Search in Binary Space

Cited by 8 publications

References 17 publications

Modifying Hamming Spaces for Efficient Search

Modifying Hamming Spaces for Efficient Search

Efficient Testing of Physically Unclonable Functions for Uniqueness

Deep Spherical Quantization for Image Search

Contact Info

Product

Resources

About