FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
Paper • 2506.11543 • Published
FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
This repository contains the official PyTorch implementation for the [CVPR 2025 Highlight] paper "FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation".
The code is available at GitHub
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support