Compact hashing with joint optimization of search accuracy and time

He, Junfeng; Chang, Shih-Fu; Radhakrishnan, Regunathan; Bauer, Claus

doi:10.1109/cvpr.2011.5995518

Cited by 97 publications

(63 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To some extend, the hash bits of each local feature can also be viewed as the visual word index, however, the advantages of using hash bits are: 1) In "bag of words" representation, the distance between "word index" of local features is meaningless. For example, word index 4 is not "meaningfully" closer to word index 5 than word index 200, since word index are just clustering labels; however, the hamming distance between the hash bits is actually meaningful when we use similarity preserving hash functions, like PCA hashing, SPICA hashing [9] or LSH [5]. The hamming distance among hash bits is often designed to approximate the original feature distance, and hence is helpful for matching local features much more accurately.…”

Section: Motivations and Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Mobile product search with bag of hash bits

Lin

Feng

et al. 2011

Proceedings of the 19th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Motivations and Contributionsmentioning

confidence: 99%

“…Use compact hashing (e.g., PCA hashing (PCH) or SPICA hashing [9]) instead of random hash functions like Locality Sensitive Hashing (LSH) [5].…”

Section: Motivations and Contributionsmentioning

confidence: 99%

Mobile product search with bag of hash bits

Lin

Feng

et al. 2011

Proceedings of the 19th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

show abstract

“…Spectral hashing (SH) [7] and anchor graph hashing (AGH) [8], which are formulated based on a graph partitioning problem, are regarded as being an unsupervised learning method. Other unsupervised methods have been proposed such as [9], [10], which construct the binary hash function that uniformly assigns the data to each binary pattern to the extent possible. On the other hand, there are supervised-learning-based methods that use the information of the similar or dissimilar label of pairwise data.…”

Section: Construction Of the Binary Hash Functionmentioning

confidence: 99%

Multiple Binary Codes for Fast Approximate Similarity Search

Shirakawa

2015

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYOne of the fast approximate similarity search techniques is a binary hashing method that transforms a real-valued vector into a binary code. The similarity between two binary codes is measured by their Hamming distance. In this method, a hash table is often used when undertaking a constant-time similarity search. The number of accesses to the hash table, however, increases when the number of bits lengthens. In this paper, we consider a method that does not access data with a long Hamming radius by using multiple binary codes. Further, we attempt to integrate the proposed approach and the existing multi-index hashing (MIH) method to accelerate the performance of the similarity search in the Hamming space. Then, we propose a learning method of the binary hash functions for multiple binary codes. We conduct an experiment on similarity search utilizing a dataset of up to 50 million items and show that our proposed method achieves a faster similarity search than that possible with the conventional linear scan and hash table search. key words: similarity search, binary hash, approximate nearest neighbor search, machine learning, image retrieval

show abstract

“…For example, Torralba et al [2008] showed that both stacked-restricted boltzmann machine (stacked-RBM for short) method and similarity sensitive coding (SSC) method work significantly better than LSH-based methods while applying to real applications containing tens of millions of data points. He et al [2011] developed a new hashing algorithm to explicitly optimize search accuracy as well as search time. Liu et al [2011] proposed a novel anchor graph hashing method to automatically discover the neighborhood structure inherent in the data, aim at learning appropriate compact codes.…”

Section: Related Workmentioning

confidence: 99%

Sparse hashing for fast multimedia search

Zhu

Huang

Cheng

et al. 2013

ACM Trans. Inf. Syst.

103

View full text Add to dashboard Cite

Hash-based methods achieve fast similarity search by representing high-dimensional data with compact binary codes. However, both generating binary codes and encoding unseen data effectively and efficiently remain very challenging tasks. In this article, we focus on these tasks to implement approximate similarity search by proposing a novel hash based method named sparse hashing (SH for short). To generate interpretable (or semantically meaningful) binary codes, the proposed SH first converts original data into lowdimensional data through a novel nonnegative sparse coding method. SH then converts the low-dimensional data into Hamming space (i.e., binary encoding low-dimensional data) by a new binarization rule. After this, training data are represented by generated binary codes. To efficiently and effectively encode unseen data, SH learns hash functions by taking a-priori knowledge into account, such as implicit group effect of the features in training data, and the correlations between original space and the learned Hamming space. SH is able to perform fast approximate similarity search by efficient bit XOR operations in the memory of a modern PC with short binary code representations. Experimental results show that the proposed SH significantly outperforms state-of-the-art techniques.

show abstract

Compact hashing with joint optimization of search accuracy and time

Abstract: Abstract

Cited by 97 publications

References 17 publications

Mobile product search with bag of hash bits

Mobile product search with bag of hash bits

Multiple Binary Codes for Fast Approximate Similarity Search

Sparse hashing for fast multimedia search

Contact Info

Product

Resources

About