Adaptive Training of Random Mapping for Data Quantization

by   Miao Cheng, et al.

Data quantization learns encoding results of data with certain requirements, and provides a broad perspective of many real-world applications to data handling. Nevertheless, the results of encoder is usually limited to multivariate inputs with the random mapping, and side information of binary codes are hardly to mostly depict the original data patterns as possible. In the literature, cosine based random quantization has attracted much attentions due to its intrinsic bounded results. Nevertheless, it usually suffers from the uncertain outputs, and information of original data fails to be fully preserved in the reduced codes. In this work, a novel binary embedding method, termed adaptive training quantization (ATQ), is proposed to learn the ideal transform of random encoder, where the limitation of cosine random mapping is tackled. As an adaptive learning idea, the reduced mapping is adaptively calculated with idea of data group, while the bias of random transform is to be improved to hold most matching information. Experimental results show that the proposed method is able to obtain outstanding performance compared with other random quantization methods.


page 1

page 2

page 3

page 4


Ternary and Binary Quantization for Improved Classification

Dimension reduction and data quantization are two important methods for ...

Smart Ternary Quantization

Neural network models are resource hungry. Low bit quantization such as ...

Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples

Model quantization is known as a promising method to compress deep neura...

CRH: A Simple Benchmark Approach to Continuous Hashing

In recent years, the distinctive advancement of handling huge data promo...

Adaptive Matching of Kernel Means

As a promising step, the performance of data analysis and feature learni...

Deep Recurrent Quantization for Generating Sequential Binary Codes

Quantization has been an effective technology in ANN (approximate neares...

In-Depth DCT Coefficient Distribution Analysis for First Quantization Estimation

The exploitation of traces in JPEG double compressed images is of utter ...

Please sign up or login with your details

Forgot password? Click here to reset