Related papers: StatQAT: Statistical Quantizer Optimization for De…

The diffusion model has gained popularity in vision applications due to its remarkable generative performance and versatility. However, high storage and computation demands, resulting from the model size and iterative generation, hinder its…

Diffusion models have shown remarkable performance in image synthesis by progressively estimating a smooth transition from a Gaussian distribution of noise to a real image. Unfortunately, their practical deployment is limited by slow…

Deep learning algorithms achieve high classification accuracy at the expense of significant computation cost. In order to reduce this cost, several quantization schemes have gained attention recently with some focusing on weight…

Quantization enables efficient acceleration of deep neural networks by reducing model memory footprint and exploiting low-cost integer math hardware units. Quantization maps floating-point weights and activations in a trained model to…

To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into low-bitwidth numbers without significant accuracy…

Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous…

Deep learning methods have established a significant place in image classification. While prior research has focused on enhancing final outcomes, the opaque nature of the decision-making process in these models remains a concern for…

Quantization-Aware Training (QAT) is a critical technique for deploying deep neural networks on resource-constrained devices. However, existing methods often face two major challenges: the highly non-uniform distribution of activations and…

Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision…

Recent work has explored reduced numerical precision for parameters, activations, and gradients during neural network training as a way to reduce the computational cost of training (Na & Mukhopadhyay, 2016) (Courbariaux et al., 2014). We…

A prominent technique for reducing the memory footprint of Spiking Neural Networks (SNNs) without decreasing the accuracy significantly is quantization. However, the state-of-the-art only focus on employing the weight quantization directly…

Quantization has become a crucial step for the efficient deployment of deep neural networks, where floating point operations are converted to simpler fixed point operations. In its most naive form, it simply consists in a combination of…

Medical image classification is a critical task in healthcare, enabling accurate and timely diagnosis. However, deploying deep learning models on resource-constrained edge devices presents significant challenges due to computational and…

Neural network quantization is widely used to reduce model inference complexity in real-world deployments. However, traditional integer quantization suffers from accuracy degradation when adapting to various dynamic ranges. Recent research…

Processing-in-memory (PIM), an increasingly studied neuromorphic hardware, promises orders of energy and throughput improvements for deep learning inference. Leveraging the massively parallel and efficient analog computing inside memories,…

Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work, we cast NN quantization as a discrete labelling problem, and…

The quantization of neural networks for the mitigation of the nonlinear and components' distortions in dual-polarization optical fiber transmission is studied. Two low-complexity neural network equalizers are applied in three 16-QAM 34.4…

Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.…

Neural network quantization aims to accelerate and trim full-precision neural network models by using low bit approximations. Methods adopting the quantization aware training (QAT) paradigm have recently seen a rapid growth, but are often…

INT8 quantization has become one of the standard techniques for deploying convolutional neural networks (CNNs) on edge devices to reduce the memory and computational resource usages. By analyzing quantized performances of existing…