IEEE

Improving the Post-Training Neural Network Quantization by Prepositive Feature Quantization

Abstract: Post-training neural network quantization (PTQ) is an effective model compression technology that has revolutionized the deployment of deep neural networks on various edge devices. It ...
GitHub

APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers

This repository contains the official PyTorch implementation for the CVPR 2025 paper "APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision ...
GitHub

ailia-ai/onnx-quantization

This is a example to quantize onnx. The input is onnx of float. Quantization is done using onnxruntime. The output is onnx of int8. The default is to quantize using only 2 images, which is less ...
IEEE

Vector Quantized Semantic Communication System

Abstract: Although analog semantic communication systems have received considerable attention in the literature, there is less work on digital semantic communication systems. In this letter, we ...