Hashing with binary autoencoders

By M. A. Carreira-Perpiñán, Ramin Raziperchikolaei. 2015

184 citations recorded by the source corpus.

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. Finding the optimal hash function is difficult because it involves binary constraints, and most approaches approximate the optimization by relaxing the constraints and then binarizing the result. Here, we focus on the binary autoencoder model, which seeks to reconstruct an image from the binary code produced by the hash function. We show that the optimization can be simplified with the method of auxiliary coordinates. This reformulates the optimization as alternating two easier steps: one that learns the encoder and decoder separately, and one that optimizes the code for each image. Image retrieval experiments show the resulting hash function outperforms or is competitive with state-of-the-art methods for binary hashing.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, methodology): “Although the approach to generate the binary AE is different from the previous one, since they achieve hashing with binary AEs helped by MAC (Method of Auxiliary Coordinates) [134], the proposal in [135] is quite similar.”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “Results and Discussion: We applied the precision-recall curves and the mean average precision (mAP) measures to evaluate the efficacy of the hashing methods, similar to previous research [7, 11, 21].”
A Survey on Learning to Hash (2016, methodology): “A variant method proposed in [13] reconstructs the input vector from the binary codes, which is effectively solved using the auxiliary coordinates algorithm.”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “Different types of networks are used to learn the binary description such as deep neural networks [87], convolutional neural networks [56], autoencoder networks [64], [152], siamese networks [156], triplet networks [112], generative adversarial networks [110], [171], [175], and deep variational netw”
NASH: Toward End-to-End Neural Architecture for Generative Semantic Hashing (2018, background): “, 2017) or binary autoencoder (Carreira-Perpinán and Raziperchikolaei, 2015), where a linear decoder is typically adopted to obtain promising retrieval results.”
Deep Cross-Modal Hashing (2016, background): “Due to its low storage cost and fast retrieval speed, hashing has recently attracted much attention from the ANN research community [17, 34, 9, 15, 26, 10, 29, 21, 28, 4].”