MetaAug: Meta-Data Augmentation for Post-Training Quantization

TL;DR

MetaAug introduces a meta-learning approach that uses data transformation and validation to improve post-training quantization, reducing overfitting and enhancing model performance on limited calibration data.

Contribution

The paper proposes a novel meta-learning based method that jointly optimizes a data transformation network and a quantized model using bi-level optimization, improving PTQ results.

Findings

Outperforms state-of-the-art PTQ methods on ImageNet

Effectively mitigates overfitting in PTQ

Enhances quantized model accuracy across various architectures

Abstract

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a large training set is not available. However, it often leads to overfitting on the small calibration dataset. Several methods have been proposed to address this issue, yet they still rely on only the calibration set for the quantization and they do not validate the quantized model due to the lack of a validation set. In this work, we propose a novel meta-learning based approach to enhance the performance of post-training quantization. Specifically, to mitigate the overfitting problem, instead of only training the quantized model using the original calibration set without any validation during the learning process as in previous PTQ works, in our approach, we both train and validate the quantized model using two different sets of images. In particular, we propose a meta-learning based approach to jointly optimize a transformation network and a quantized model through bi-level optimization. The transformation network modifies the original calibration data and the modified data will be used as the training set to learn the quantized model with the objective that the quantized model achieves a good performance on the original calibration data. Extensive experiments on the widely used ImageNet dataset with different neural network architectures demonstrate that our approach outperforms the state-of-the-art PTQ methods.