Hashing with binary autoencoders

Abstract

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, using precision/recall and a measure of code utilization, show the resulting hash function outperforms or is competitive with state-of-the-art methods for binary hashing.

22 pages, 11 figures

References in corpus (3)

• Fast Supervised Hashing with Decision Trees for High-Dimensional Data
• Distributed optimization of deeply nested systems
• An ADMM algorithm for solving a proximal bound-constrained quadratic program

Cited by in corpus (9)

• Stochastic Generative Hashing
• Simultaneous Feature Aggregating and Hashing for Large-scale Image Search
• From Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
• Asymmetric Deep Supervised Hashing
• Embedding based on function approximation for large scale image search
• Simultaneous Compression and Quantization: A Joint Approach for Efficient Unsupervised Hashing
• Supervised Quantization for Similarity Search
• Discrete Latent Factor Model for Cross-Modal Hashing
• Binary Hashing with Semidefinite Relaxation and Augmented Lagrangian