paper-with-me

Papers

Data-Free Quantization Through Weight Equalization and Bias Correction

2019-06-11 · ICCV 2019 10 · Markus Nagel, Mart van Baalen, Tijmen Blankevoort, Max Welling

We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit fixed-point quantization is essential for efficient inference on modern deep learning hardware. However, quantizing models to run in 8-bit is a non-trivial task, frequently leading to either significant performance reduction or engineering time spent on training a network to be amenable to quantization. Our approach relies on equalizing the weight ranges in the network by making use of a scale-equivariance property of activation functions. In addition the method corrects biases in the error that are introduced during quantization. This improves quantization accuracy performance, and can be applied to many common computer vision architectures with a straight forward API call. For common architectures, such as the MobileNet family, we achieve state-of-the-art quantized model performance. We further show that the method also extends to other computer vision architectures and tasks such as semantic segmentation and object detection.

📄 PDF Abstract BibTeX arXiv:1906.04721

Code (5)

ANSHUMAN87/Bias-Correction pytorch
Jangho-Kim/PSG-pytorch pytorch
KwangHoonAn/Quantizations pytorch
jakc4103/DFQ pytorch
raja-kumar/folding-batchnorm pytorch

Tasks

Data Free Quantizationobject-detectionObject DetectionQuantizationSemantic Segmentation

Similar Papers 제목 키워드 기반

AWEQ: Post-Training Quantization with Activation-Weight Equalization for Large Language Models

2023-11-02 · Baisong Li, Xingwang Wang, Haixiao Xu

Large language models(LLMs) exhibit excellent performance across a variety of tasks, but they come with significant computational and storage costs. Quantizing these models is an effective way to alleviate this issue. Ho…

Quantization

Designing strong baselines for ternary neural network quantization through support and mass equalization

2023-06-30 · Edouard Yvinec, Arnaud Dapogny, Kevin Bailly

Deep neural networks (DNNs) offer the highest performance in a wide range of applications in computer vision. These results rely on over-parameterized backbones, which are expensive to run. This computational burden can …

Quantization

FPTQ: Fine-grained Post-Training Quantization for Large Language Models

2023-08-30 · Qingyuan Li, Yifan Zhang, Liang Li, Peng Yao 외

In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackl…

Quantization

Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization

2025-05-16 · Shihao Zhang, Haoyu Zhang, Ian Colbert, Rayan Saab

We introduce Qronos -- a new state-of-the-art post-training quantization algorithm that sequentially rounds and updates neural network weights. Qronos not only explicitly corrects errors due to both weight and activation…

QuantizationText Generation

From 2:4 to 8:16 sparsity patterns in LLMs for Outliers and Weights with Variance Correction

2025-07-03 · Egor Maximov, Yulia Kuzkina, Azamat Kanametov, Alexander Prutko 외 arxiv

As large language models (LLMs) grow in size, efficient compression techniques like quantization and sparsification are critical. While quantization maintains performance with reduced precision, structured sparsity metho…