26 papers · ranked by Valyu relevance
Liefu Ai, Yong Tao, Hongjun Cheng, Yuanzhi Wang + 3 more
'Deyang Liu' 'Xin Zheng'] To further improve the approximate nearest neighbor (ANN) search performance, an accumulative quantization (AQ) is proposed and applied to effective ANN search. It approximates a vector with the accumulation of several centroids, each of which is selected from a different codebook. To provide…
Alexander Engelsberger, Thomas Villmann, Rosario Lo Franco, GuiLu Long
'GuiLu Long'] In the field of machine learning, vector quantization is a category of low-complexity approaches that are nonetheless powerful for data representation and clustering or classification tasks. Vector quantization is based on the idea of representing a data or a class distribution using a small set of…
Verusca Severo, Felipe B. S. Ferreira, Rodrigo Spencer, Arthur Nascimento + 2 more
'Arthur Nascimento' 'Francisco Madeiro' 'Steve Vanlanduit'] Vector Quantization (VQ) is a technique with a wide range of applications. For example, it can be used for image compression. The codebook design for VQ has great significance in the quality of the quantized signals and can benefit from the use of swarm…
Piyush Kumar Pareek, Chethana Sridhar, R. Kalidoss, Muhammad Aslam + 3 more
Due to the increasing number of medical imaging images being utilized for the diagnosis and treatment of diseases, lossy or improper image compression has become more prevalent in recent years. The compression ratio and image quality, which are commonly quantified by PSNR values, are used to evaluate the performance of…
Qijiong Liu, Xiaoyu Dong, Jiaren Xiao, Nuo Chen + 5 more
'Jieming Zhu' 'Chenxu Zhu' 'Tetsuya Sakai' 'Xiao-Ming Wu'] Vector quantization, renowned for its unparalleled feature compression capabilities, has been a prominent topic in signal processing and machine learning research for several decades and remains widely utilized today. With the emergence of large models and…
Tagir Akhmetshin, Arkadii Lin, Timur Madzhidov, Alexandre Varnek
Autoencoders represent a promising technique for the inverse quantitative structure-activity relationship (QSAR) task. However, undesirable bias, such as atom ordering, affects the neighbourhood behaviour of autoencoders’ latent space and, consequently, usage of the latent vectors as variables in machine-learning…
Muhammmad Bilal, Zahid Ullah, Omer Mujahid, Tama Fouzder + 1 more
Vector quantization (VQ) is a block coding method that is famous for its high compression ratio and simple encoder and decoder implementation. Linde-Buzo-Gray (LBG) is a renowned technique for VQ that uses a clustering-based approach for finding the optimum codebook. Numerous algorithms, such as Particle Swarm…
Dawei Shen, Yao-zhong Zhang, Seiya Imoto
Whole Slide Images (WSIs) are gigapixel, high-resolution digital scans of microscope slides, providing detailed tissue profiles for pathological analysis. Due to their gigapixel size and lack of detailed annotations, Multiple Instance Learning (MIL) becomes the primary technique for WSI analysis. However, current MIL…
C.C. Hang, Sankepally Sainath Reddy, Ziwei Chen, Dianbo Liu
Quantization Authors: ['C.C. Hang' 'Sankepally Sainath Reddy' 'Ziwei Chen' 'Dianbo Liu'] The dimensionality of the embedding and the number of available embeddings ( also called codebook size) are critical factors influencing the performance of Vector Quantization(VQ), a discretization process used in many models such…
Jaeyung Kim, YoungJoon Yoo
Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However, VQ-VAE models must tokenize entire images using a finite set of codebook vectors, and this capacity limitation restricts their ability to capture rich and diverse…
Runsen Feng, Zongyu Guo, Weiping Li, Zhibo Chen
In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance [34]. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding (NTC) with uniform scalar quantization, overlooking the benefits of VQ due to…
Hui Zheng, Hai-Teng Wang, Wei-Bang Jiang, Zhong-Tao Chen + 5 more
While invasive brain-computer interfaces have shown promise for high-performance speech decoding under medical use, the potential of intracranial stereoElectroEn-cephaloGraphy (sEEG), which causes less damage to patients, remains underex-plored. With the rapid progress in representation learning, leveraging abundant…
Yifan Wang, Zhanxuan Mei, Ioannis Katsavounidis, C.‐C. Jay Kuo
—A multi-grid multi-block-size vector quantization (MGBVQ) method is proposed for image coding in this work. The fundamental idea of image coding is to remove correlations among pixels before quantization and entropy coding, e.g., the discrete cosine transform (DCT) and intra predictions, adopted by modern image coding…
Yue Zhao, Yuanjun Xiong, Philipp Krähenbühl
We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1) parameter-efficient without an explicit codebook, (2) scalable to arbitrary token…
Mahdi Pourmirzaei, Alex Morehead, Farzaneh Esmaili, Jarett Ren + 2 more
Converting protein tertiary structure into discrete tokens via vector-quantized variational autoencoders (VQ-VAEs) creates a language of 3D geometry and provides a natural interface between sequence and structure models. While pose invariance is commonly enforced, retaining chirality and directional cues without…
Mahdi Pourmirzaei, Alex Morehead, Farzaneh Esmaili, Jarett Ren + 2 more
Converting protein tertiary structure into discrete tokens via vector-quantized variational autoencoders (VQ-VAEs) creates a language of 3D geometry and provides a natural interface between sequence and structure models. While pose invariance is commonly enforced, retaining chirality and directional cues without…
Kazuhisa Fujita, Muhammad Aleem
The growth of network-connected devices has led to an exponential increase in data generation, creating significant challenges for efficient data analysis. This data is generated continuously, creating a dynamic flow known as a data stream. The characteristics of a data stream may change dynamically, and this change is…
Yufeng Liu, Linghui Chen, Haiyan Liu
The power of diffusion probabilistic models (DDPMs) in protein design was recently demonstrated by methods that performs three-dimensional protein backbone denoising. However, these DDPMs tend to generate protein backbones of idealized secondary structures and short loops, lacking diverse, non-idealized local…
Seungcheol Park, Jeongin Bae, Beomseok Kwon, Min-Jun Kim + 4 more
How can we quantize large language models while preserving accuracy? Quantization is essential for deploying large language models (LLMs) efficiently. Binary-coding quantization (BCQ) and uniform quantization (UQ) are promising quantization schemes that have strong expressiveness and optimizability, respectively.…
Pumiao Yan, Dante G. Muratore, E.J. Chichilnisky, Boris Murmann + 1 more
Scaling neural recording systems to thousands of channels creates extreme bandwidth demands, posing a challenge for resource-constrained, implantable devices. This work introduces an adaptive, multi-stage compression framework for high-bandwidth neural interfaces. The system combines a Wired-OR analog-to-digital…
Anthony Onwuli, Keith T. Butler, Aron Walsh
High-dimensional representations of the elements have become common within the field of materials informatics to build useful, structure-agnostic models for the chemistry of materials. However, the characteristics of elements change when they adopt a given oxidation state, with distinct structural preferences and…
Zhihao Lan, WanZhen Liang
The variational quantum eigensolver (VQE) algorithm can simulate the chemical systems such as molecules in the noisy intermediate-scale quantum devices and shows promising applications in quantum chemistry simulations. The accuracy and computational cost of the VQE simulations are determined by the underlying Ansätze.…
Sara Giarrusso, Paola Gori-Giorgi, Federica Agostini
We generalize the definitions of local scalar potentials named vkin and vN−1, which are relevant to properly describe phenomena such as molecular dissociation with density-functional theory, to the case in which the electronic wavefunction corresponds to a complex current-carrying state. In such a case, an extra term…
Authors not listed
We present a comprehensive theoretical analysis of quantum subspace diagonalization methods for molecular electronic structure calculations, establishing rigorous complexity bounds and convergence guarantees. Building on recent developments in adaptive quantum algorithms for chemical systems, we formulate a general…
H. Robert Frost
We present an approach for modeling single cell RNA-sequencing (scRNA-seq) data using quaternions. Quaternions are four dimensional hypercomplex numbers that, along with real numbers, complex numbers and octonions, represent one of the four normed division algebras. Quaternions have been most widely employed to…
Vladimir Kondratyev, Marian Dryzhakov, Timur Gimadiev, Dmitriy Slutskiy
In this work, we provide further development of the junction tree variational autoencoder (JT VAE) architecture in terms of implementation and application of the internal feature space of the model. Pretraining of JT VAE on a large dataset and further optimization with a regression model led to a latent space that can…