Stochastic Generative Hashing
Learning-based binary hashing has become a powerful paradigm for fast search and retrieval in massive databases. However, due to the requirement of discrete outputs for the hash functions, learning such functions is known to be very challenging. In addition, the objective functions adopted by existing hashing techniques are mostly chosen heuristically. In this paper, we propose a novel generative approach to learn hash functions through Minimum Description Length principle such that the learned hash codes maximally compress the dataset and can also be used to regenerate the inputs. We also develop an efficient learning algorithm based on the stochastic distributional gradient, which avoids the notorious difficulty caused by binary output constraints, to jointly optimize the parameters of the hash function and the associated generative model. Extensive experiments on a variety of large-scale datasets show that the proposed method achieves better retrieval results than the existing state-of-the-art methods.
Code (2)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
Semi-Supervised Generative Adversarial Hashing for Image Retrieval
With explosive growth of image and video data on the Internet, hashing technique has been extensively studied for large-scale visual search. Benefiting from the advance of deep learning, deep hashing methods have achieve…
Deep HashingImage RetrievalRetrievalSemantic Similarity+2Document Hashing with Mixture-Prior Generative Models
Hashing is promising for large-scale information retrieval tasks thanks to the efficiency of distance evaluation between binary codes. Generative hashing is often used to generate hashing codes in an unsupervised way. Ho…
Information RetrievalRetrievalCoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing
Leveraging supervised information can lead to superior retrieval performance in the image hashing domain but the performance degrades significantly without enough labeled data. One effective solution to boost performance…
RetrievalSCH-GAN: Semi-supervised Cross-modal Hashing by Generative Adversarial Network
Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Supervised cross-modal hashing methods have achieved c…
Generative Adversarial NetworkReinforcement LearningRetrievalSupervised Online Hashing via Hadamard Codebook Learning
In recent years, binary code learning, a.k.a hashing, has received extensive attention in large-scale multimedia retrieval. It aims to encode high-dimensional data points to binary codes, hence the original high-dimensio…
RetrievalSemantic SimilaritySemantic Textual Similarity