English

TSPTQ-ViT: Two-scaled post-training quantization for vision transformer

Image and Video Processing 2023-05-23 v1

Abstract

Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on resource-constrained edge devices. Due to the non-normally distributed values after Softmax and GeLU, post-training quantization on ViTs results in severe accuracy degradation. Moreover, conventional methods fail to address the high channel-wise variance in LayerNorm. To reduce the quantization loss and improve classification accuracy, we propose a two-scaled post-training quantization scheme for vision transformer (TSPTQ-ViT). We design the value-aware two-scaled scaling factors (V-2SF) specialized for post-Softmax and post-GeLU values, which leverage the bit sparsity in non-normal distribution to save bit-widths. In addition, the outlier-aware two-scaled scaling factors (O-2SF) are introduced to LayerNorm, alleviating the dominant impacts from outlier values. Our experimental results show that the proposed methods reach near-lossless accuracy drops (<0.5%) on the ImageNet classification task under 8-bit fully quantized ViTs.

Keywords

Cite

@article{arxiv.2305.12901,
  title  = {TSPTQ-ViT: Two-scaled post-training quantization for vision transformer},
  author = {Yu-Shan Tai and Ming-Guang Lin and An-Yeu and Wu},
  journal= {arXiv preprint arXiv:2305.12901},
  year   = {2023}
}
R2 v1 2026-06-28T10:41:12.875Z