A Binary Variational Autoencoder for Hashing
Searching a large dataset to find elements that are similar to a sample object is a fundamental problem in computer science. Hashing algorithms deal with this problem by representing data with similarity-preserving binary codes that can be used as indices into a hash table. Recently, it has been shown that variational autoencoders (VAEs) can be successfully trained to learn such codes in unsupervised and semi-supervised scenarios. In this paper, we show that a variational autoencoder with binary latent variables leads to a more natural and effective hashing algorithm that its continuous counterpart. The model reduces the quantization error introduced by continuous formulations but is still trainable with standard back-propagation. Experiments on text retrieval tasks illustrate the advantages of our model with respect to previous art.
Code (1)
Tasks
QuantizationRetrievalText RetrievalSimilar Papers 제목 키워드 기반
Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing
Semantic hashing is an emerging technique for large-scale similarity search based on representing high-dimensional data using similarity-preserving binary codes used for efficient indexing and search. It has recently bee…
Supervised Image RetrievalSupervised Text RetrievalUnsupervised Few-Bits Semantic Hashing with Implicit Topics Modeling
Semantic hashing is a powerful paradigm for representing texts as compact binary hash codes. The explosion of short text data has spurred the demand of few-bits hashing. However, the performance of existing semantic hash…
Unsupervised Neural Generative Semantic Hashing
Fast similarity search is a key component in large-scale information retrieval, where semantic hashing has become a popular strategy for representing documents as binary hash codes. Recent advances in this area have been…
Code GenerationDocument RankingInformation RetrievalRetrievalUnsupervised Semantic Hashing with Pairwise Reconstruction
Semantic Hashing is a popular family of methods for efficient similarity search in large-scale datasets. In Semantic Hashing, documents are encoded as short binary vectors (i.e., hash codes), such that semantic similarit…
DecoderSemantic SimilaritySemantic Textual SimilarityHashing with binary autoencoders
An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Fin…
DecoderImage RetrievalRetrieval