paper-with-me

홈 › Papers

A Binary Variational Autoencoder for Hashing

2019-10-22 · Lecture Notes in Computer Science 2019 10 · Francisco Mena, Ricardo Ñanculef

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.

📄 PDF Abstract BibTeX

Code (1)

fmenat/DiscreteVAE tf

Tasks

QuantizationRetrievalText Retrieval

Similar Papers 제목 키워드 기반

Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing

2020-07-17 · Ricardo Ñanculef, Francisco Mena, Antonio Macaluso, Stefano Lodi 외

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 Retrieval

Unsupervised Few-Bits Semantic Hashing with Implicit Topics Modeling

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Fanghua Ye, Jarana Manotumruksa, Emine Yilmaz

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

2019-06-03 · Casper Hansen, Christian Hansen, Jakob Grue Simonsen, Stephen Alstrup 외

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 RetrievalRetrieval

Unsupervised Semantic Hashing with Pairwise Reconstruction

2020-07-01 · Casper Hansen, Christian Hansen, Jakob Grue Simonsen, Stephen Alstrup 외

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 Similarity

Hashing with binary autoencoders

2015-01-05 · CVPR 2015 6 · Miguel Á. Carreira-Perpiñán, Ramin Raziperchikolaei

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