Topic
Feature hashing
About: Feature hashing is a research topic. Over the lifetime, 993 publications have been published within this topic receiving 51462 citations.
Papers published on a yearly basis
Papers
More filters
23 Oct 2017
TL;DR: Huang et al. as discussed by the authors proposed a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH), which is designed based on the following three principles: 1) maximizing the discrimination among image representations; 2) minimizing the quantization loss between the original real-valued feature descriptors and the learned hash codes.
Abstract: The explosive growth of multimedia contents has made hashing an indispensable component in image retrieval. In particular, learning-based hashing has recently shown great promising with the advance of Convolutional Neural Network (CNN). However, the existing hashing methods are mostly tuned for classification. Learning hash functions for retrieval tasks, especially for instance-level retrieval, still faces many challenges. Considering the difficulty in obtaining labeled datasets for image retrieval task in large scale, we propose a novel CNN-based unsupervised hashing method, namely Unsupervised Triplet Hashing (UTH). The unsupervised hashing network is designed based on the following three principles: 1) maximizing the discrimination among image representations; 2) minimizing the quantization loss between the original real-valued feature descriptors and the learned hash codes; 3) maximizing the information entropy for the learned hash codes to improve their representation ability. Extensive experiments on CIFAR-10, MNIST and In-shop datasets have shown that UTH outperforms several state-of-the-art unsupervised hashing methods in terms of retrieval accuracy.
40 citations
23 Oct 2017
TL;DR: Experiments demonstrate that the proposed pseudo label based unsupervised deep discriminative hashing method outperforms the state-of-art unsuper supervised hashing methods.
Abstract: Hashing methods play an important role in large scale image retrieval. Traditional hashing methods use hand-crafted features to learn hash functions, which can not capture the high level semantic information. Deep hashing algorithms use deep neural networks to learn feature representation and hash functions simultaneously. Most of these algorithms exploit supervised information to train the deep network. However, supervised information is expensive to obtain. In this paper, we propose a pseudo label based unsupervised deep discriminative hashing algorithm. First, we cluster images via K-means and the cluster labels are treated as pseudo labels. Then we train a deep hashing network with pseudo labels by minimizing the classification loss and quantization loss. Experiments on two datasets demonstrate that our unsupervised deep discriminative hashing method outperforms the state-of-art unsupervised hashing methods.
40 citations
TL;DR: The application of line features for geometric hashing to the recognition of two-dimensional (2D) (or flat 3D) objects undergoing various geometric transformations is investigated.
40 citations
TL;DR: A more generalized multi-layer LSPH framework, in which hierarchical representations can be effectively learned by a multiplicative up-propagation algorithm, and Experimental results on three large-scale retrieval datasets show that ML-LSPH can achieve better performance than the single-layer lSPH and both of them outperform existing hashing techniques on large- scale data.
Abstract: Aiming at efficient similarity search, hash functions are designed to embed high-dimensional feature descriptors to low-dimensional binary codes such that similar descriptors will lead to binary codes with a short distance in the Hamming space. It is critical to effectively maintain the intrinsic structure and preserve the original information of data in a hashing algorithm. In this paper, we propose a novel hashing algorithm called Latent Structure Preserving Hashing (LSPH), with the target of finding a well-structured low-dimensional data representation from the original high-dimensional data through a novel objective function based on Nonnegative Matrix Factorization (NMF) with their corresponding Kullback-Leibler divergence of data distribution as the regularization term. Via exploiting the joint probabilistic distribution of data, LSPH can automatically learn the latent information and successfully preserve the structure of high-dimensional data. To further achieve robust performance with complex and nonlinear data, in this paper, we also contribute a more generalized multi-layer LSPH (ML-LSPH) framework, in which hierarchical representations can be effectively learned by a multiplicative up-propagation algorithm. Once obtaining the latent representations, the hash functions can be easily acquired through multi-variable logistic regression. Experimental results on three large-scale retrieval datasets, i.e., SIFT 1M, GIST 1M and 500 K TinyImage, show that ML-LSPH can achieve better performance than the single-layer LSPH and both of them outperform existing hashing techniques on large-scale data.
40 citations
01 Oct 2016
TL;DR: Binary optimized hashing (BOH) is proposed, in which it is proved that if the loss function is Lipschitz continuous, the binary optimization problem can be relaxed to a bound-constrained continuous optimization problem.
Abstract: This paper studies the problem of learning to hash, which is essentially a mixed integer optimization problem, containing both the binary hash code output and the (continuous) parameters forming the hash functions. Different from existing relaxation methods in hashing, which have no theoretical guarantees for the error bound of the relaxations, we propose binary optimized hashing (BOH), in which we prove that if the loss function is Lipschitz continuous, the binary optimization problem can be relaxed to a bound-constrained continuous optimization problem. Then we introduce a surrogate objective function, which only depends on unbinarized hash functions and does not need the slack variables transforming unbinarized hash functions to discrete functions, to approximate the relaxed objective function. We show that the approximation error is bounded and the bound is small when the problem is optimized. We apply the proposed approach to learn hash codes from either handcraft feature inputs or raw image inputs. Extensive experiments are carried out on three benchmarks, demonstrating that our approach outperforms state-of-the-arts with a significant margin on search accuracies.
40 citations