Codebook

About: Codebook is a research topic. Over the lifetime, 8492 publications have been published within this topic receiving 115995 citations.

Deep Triplet Quantization

Abstract: Deep hashing establishes efficient and effective image retrieval by end-to-end learning of deep representations and hash codes from similarity data. We present a compact coding solution, focusing on deep learning to quantization approach that has shown superior performance over hashing solutions for similarity retrieval. We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets. To enable more effective triplet training, we design a new triplet selection approach, Group Hard, that randomly selects hard triplets in each image group. To generate compact binary codes, we further apply a triplet quantization with weak orthogonality during triplet training. The quantization loss reduces the codebook redundancy and enhances the quantizability of deep representations through back-propagation. Extensive experiments demonstrate that DTQ can generate high-quality and compact binary codes, which yields state-of-the-art image retrieval performance on three benchmark datasets, NUS-WIDE, CIFAR-10, and MS-COCO.

A fast exact GLA based on code vector activity detection

Abstract: This paper introduces a new method for reducing the number of distance calculations in the generalized Lloyd algorithm (GLA), which is a widely used method to construct a codebook in vector quantization. Reduced comparison search detects the activity of the code vectors and utilizes it on the classification of the training vectors. For training vectors whose current code vector has not been modified, we calculate distances only to the active code vectors. A large proportion of the distance calculations can be omitted without sacrificing the optimality of the partition. The new method is included in several fast GLA variants reducing their running times over 50% on average.

Turbo-Like Beamforming Based on Tabu Search Algorithm for Millimeter-Wave Massive MIMO Systems

Abstract: For millimeter-wave (mmWave) massive multiple-input–multiple-output (MIMO) systems, codebook-based analog beamforming (including transmit precoding and receive combining) is usually used to compensate the severe attenuation of mmWave signals. However, conventional beamforming schemes involve complicated search among predefined codebooks to find out the optimal pair of analog precoder and analog combiner. To solve this problem, by exploring the idea of turbo equalizer together with the tabu search (TS) algorithm, we propose a Turbo-like beamforming scheme based on TS, which is called Turbo-TS beamforming in this paper, to achieve near-optimal performance with low complexity. Specifically, the proposed Turbo-TS beamforming scheme is composed of the following two key components: 1) Based on the iterative information exchange between the base station (BS) and the user, we design a Turbo-like joint search scheme to find out the near-optimal pair of analog precoder and analog combiner; and 2) inspired by the idea of the TS algorithm developed in artificial intelligence, we propose a TS-based precoding/combining scheme to intelligently search the best precoder/combiner in each iteration of Turbo-like joint search with low complexity. Analysis shows that the proposed Turbo-TS beamforming can considerably reduce the searching complexity, and simulation results verify that it can achieve near-optimal performance.

Beamforming with Limited Feedback in Amplify-and-Forward Cooperative Networks

Abstract: A relay selection approach has previously been shown to outperform repetition-based scheduling for both amplify-and-forward (AF) and decode-and-forward (DF) cooperative networks. The selection method generally requires some feedback from the destination to the relays and the source, raising the issue of the interplay between performance and feedback rate. In this paper, we treat selection as an instance of limited- feedback distributed beamforming in cooperative AF networks, and highlight the differences between transmit beamforming in a traditional multi-input single-output (MISO) system and the distributed case. Specifically, Grassmanian line packing (GLP) is no longer the optimal codebook design, and orthogonal codebooks are no longer equivalent to each other. We derive the high signal-to-noise ratio expressions for outage probability and probability of symbol error for unlimited-feedback and selection schemes. The gap in performance between unlimited-feedback and selection beamforming is found analytically to grow rapidly with the number of relays. We compare the selection protocol to a limited-feedback distributed beamformer that assigns codebooks based on the generalized lloyd algorithm (GLA), and one that uses random beam-vectors. The main conclusion is that the performance improvement to be seen using the very complex GLA is small, and that many more feedback bits are required with random beamforming than selection for the same performance. These results indicate that the selection protocol is a very attractive protocol with low-complexity that provides excellent performance relative to other known methods.