scholarly journals Learning Deep Unsupervised Binary Codes for Image Retrieval

2018 ◽  
Author(s):  
Junjie Chen ◽  
William K. Cheung ◽  
Anran Wang
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Multimedia Retrieval ◽  
Binary Codes ◽  
Linear Transformations ◽  
Neighbor Search ◽  
Compact Representations ◽  
The Difference

Hashing is an efficient approximate nearest neighbor search method and has been widely adopted for large-scale multimedia retrieval. While supervised learning is more popular for the data-dependent hashing, deep unsupervised hashing methods have recently been developed to learn non-linear transformations for converting multimedia inputs to binary codes. Most of existing deep unsupervised hashing methods make use of a quadratic constraint for minimizing the difference between the compact representations and the target binary codes, which inevitably causes severe information loss. In this paper, we propose a novel deep unsupervised method called DeepQuan for hashing. The DeepQuan model utilizes a deep autoencoder network, where the encoder is used to learn compact representations and the decoder is for manifold preservation. To contrast with the existing unsupervised methods, DeepQuan learns the binary codes by minimizing the quantization error through product quantization technique. Furthermore, a weighted triplet loss is proposed to avoid trivial solution and poor generalization. Extensive experimental results on standard datasets show that the proposed DeepQuan model outperforms the state-of-the-art unsupervised hashing methods for image retrieval tasks.

A Meta-Algorithm for Improving Top-N Prediction Efficiency of Matrix Factorization Models in Collaborative Filtering

2019 ◽  
Vol 34 (03) ◽  
pp. 2059007
Author(s):  
A. Murat Yagci ◽  
Tevfik Aytekin ◽  
Fikret S. Gurgen
Keyword(s):  
Collaborative Filtering ◽  
Matrix Factorization ◽  
Large Scale ◽  
Nearest Neighbor ◽  
Nearest Neighbor Search ◽  
Space Efficiency ◽  
Neighbor Search ◽  
Prediction Time ◽  
Low Dimensional ◽  
Prediction Efficiency

Matrix factorization models often reveal the low-dimensional latent structure in high-dimensional spaces while bringing space efficiency to large-scale collaborative filtering problems. Improving training and prediction time efficiencies of these models are also important since an accurate model may raise practical concerns if it is slow to capture the changing dynamics of the system. For the training task, powerful improvements have been proposed especially using SGD, ALS, and their parallel versions. In this paper, we focus on the prediction task and combine matrix factorization with approximate nearest neighbor search methods to improve the efficiency of top-N prediction queries. Our efforts result in a meta-algorithm, MMFNN, which can employ various common matrix factorization models, drastically improve their prediction efficiency, and still perform comparably to standard prediction approaches or sometimes even better in terms of predictive power. Using various batch, online, and incremental matrix factorization models, we present detailed empirical analysis results on many large implicit feedback datasets from different application domains.

Optimized K-Means Hashing for Approximate Nearest Neighbor Search

2014 ◽  
Vol 651-653 ◽  
pp. 2168-2171
Author(s):  
Qin Zhen Guo ◽  
Zhi Zeng ◽  
Shu Wu Zhang ◽  
Yuan Zhang ◽  
Gui Xuan Zhang
Keyword(s):  
High Efficiency ◽  
Nearest Neighbor ◽  
Quantization Error ◽  
Nearest Neighbor Search ◽  
Binary Codes ◽  
Neighborhood Structure ◽  
Approximate Nearest Neighbor Search ◽  
Approximate Nearest Neighbor ◽  
Neighbor Search ◽  
Hamming Space

Hashing which maps data into binary codes in Hamming space has attracted more and more attentions for approximate nearest neighbor search due to its high efficiency and reduced storage cost. K-means hashing (KH) is a novel hashing method which firstly quantizes the data by codewords and then uses the indices of codewords to encode the data. However, in KH, only the codewords are updated to minimize the quantization error and affinity error while the indices of codewords remain the same after they are initialized. In this paper, we propose an optimized k-means hashing (OKH) method to encode data by binary codes. In our method, we simultaneously optimize the codewords and the indices of them to minimize the quantization error and the affinity error. Our OKH method can find both the optimal codewords and the optiaml indices, and the resulting binary codes in Hamming space can better preserve the original neighborhood structure of the data. Besides, OKH can further be generalized to a product space. Extensive experiments have verified the superiority of OKH over KH and other state-of-the-art hashing methods.

Sign in / Sign up

Export Citation Format

Share Document