English

SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization

Computer Vision and Pattern Recognition 2023-08-24 v2

Abstract

Mixed-precision quantization (MPQ) suffers from the time-consuming process of searching the optimal bit-width allocation i.e., the policy) for each layer, especially when using large-scale datasets such as ISLVRC-2012. This limits the practicality of MPQ in real-world deployment scenarios. To address this issue, this paper proposes a novel method for efficiently searching for effective MPQ policies using a small proxy dataset instead of the large-scale dataset used for training the model. Deviating from the established norm of employing a consistent dataset for both model training and MPQ policy search stages, our approach, therefore, yields a substantial enhancement in the efficiency of MPQ exploration. Nonetheless, using discrepant datasets poses challenges in searching for a transferable MPQ policy. Driven by the observation that quantization noise of sub-optimal policy exerts a detrimental influence on the discriminability of feature representations -- manifesting as diminished class margins and ambiguous decision boundaries -- our method aims to identify policies that uphold the discriminative nature of feature representations, i.e., intra-class compactness and inter-class separation. This general and dataset-independent property makes us search for the MPQ policy over a rather small-scale proxy dataset and then the policy can be directly used to quantize the model trained on a large-scale dataset. Our method offers several advantages, including high proxy data utilization, no excessive hyper-parameter tuning, and high searching efficiency. We search high-quality MPQ policies with the proxy dataset that has only 4% of the data scale compared to the large-scale target dataset, achieving the same accuracy as searching directly on the latter, improving MPQ searching efficiency by up to 300 times.

Keywords

Cite

@article{arxiv.2302.06845,
  title  = {SEAM: Searching Transferable Mixed-Precision Quantization Policy through Large Margin Regularization},
  author = {Chen Tang and Kai Ouyang and Zenghao Chai and Yunpeng Bai and Yuan Meng and Zhi Wang and Wenwu Zhu},
  journal= {arXiv preprint arXiv:2302.06845},
  year   = {2023}
}
R2 v1 2026-06-28T08:39:32.082Z