Related papers: MVQ:Towards Efficient DNN Compression and Accelera…

Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and…

We investigate the compression of deep neural networks by quantizing their weights and activations into multiple binary bases, known as multi-bit networks (MBNs), which accelerate the inference and reduce the storage for the deployment on…

Deep Learning Architectures employ heavy computations and bulk of the computational energy is taken up by the convolution operations in the Convolutional Neural Networks. The objective of our proposed work is to reduce the energy…

Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Network quantization, as a standard compression and acceleration…

In this paper, we address the problem of reducing the memory footprint of convolutional network architectures. We introduce a vector quantization method that aims at preserving the quality of the reconstruction of the network outputs rather…

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

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 as the…

Model quantization can reduce the model size and computational latency, it has become an essential technique for the deployment of deep neural networks on resourceconstrained hardware (e.g., mobile phones and embedded devices). The existing…

The number of parameters in deep neural networks (DNNs) is rapidly increasing to support complicated tasks and to improve model accuracy. Correspondingly, the amount of computations and required memory footprint increase as well.…

Energy efficiency and memory footprint of a convolutional neural network (CNN) implemented on a CNN inference accelerator depend on many factors, including a weight quantization strategy (i.e., data types and bit-widths) and mapping (i.e.,…

Residual Vector Quantization (RVQ) has become a dominant approach in neural speech and audio coding, providing high-fidelity compression. However, speech coding presents additional challenges due to real-world noise, which degrades…

The proliferation of deep learning-based machine vision applications has given rise to a new type of compression, so called video coding for machine (VCM). VCM differs from traditional video coding in that it is optimized for machine vision…

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…

Although quantum computing holds promise for solving Combinatorial Optimization Problems (COPs), the limited qubit capacity of NISQ hardware makes large-scale instances intractable. Conventional methods attempt to bridge this gap through…

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…

Spatio-temporal forecasting is crucial in various fields and requires a careful balance between identifying subtle patterns and filtering out noise. Vector quantization (VQ) appears well-suited for this purpose, as it quantizes input…

Vector quantization (VQ) is a prevalent and fundamental technique that discretizes continuous feature vectors by approximating them using a codebook. As the diversity and complexity of data and models continue to increase, there is an…

Recent state-of-the-art neural audio compression models have progressively adopted residual vector quantization (RVQ). Despite this success, these models employ a fixed number of codebooks per frame, which can be suboptimal in terms of…

We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature…

The Diffusion Transformers Models (DiTs) have transitioned the network architecture from traditional UNets to transformers, demonstrating exceptional capabilities in image generation. Although DiTs have been widely applied to…