APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
Paper
• 2504.02508 • Published
• 1
APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers
This repository contains the official PyTorch checkpoints for the CVPR 2025 paper "APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers".
The code is available at GitHub.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support