Learning to synthesize data has emerged as a promising direction in zero-shot quantization (ZSQ), which represents neural networks by low-bit integer without accessing any of the real data. In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase. To address this issue, we propose a novel zero-shot quantization method referred to as IntraQ. First, we propose a local object reinforcement that locates the target objects at different scales and positions of the synthetic images. Second, we introduce a marginal distance constraint to form class-related features distributed in a coarse area. Lastly, we devise a soft inception loss which injects a soft prior label to prevent the synthetic images from being overfitting to a fixed object. Our IntraQ is demonstrated to well retain the intra-class heterogeneity in the synthetic images and also observed to perform state-of-the-art. For example, compared to the advanced ZSQ, our IntraQ obtains 9.17\% increase of the top-1 accuracy on ImageNet when all layers of MobileNetV1 are quantized to 4-bit. Code is at https://github.com/zysxmu/IntraQ.
@article{arxiv.2111.09136,
title = {IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization},
author = {Yunshan Zhong and Mingbao Lin and Gongrui Nan and Jianzhuang Liu and Baochang Zhang and Yonghong Tian and Rongrong Ji},
journal= {arXiv preprint arXiv:2111.09136},
year = {2022}
}