English

EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices

Computer Vision and Pattern Recognition 2025-06-16 v1

Abstract

Hybrid models that combine convolutional and transformer blocks offer strong performance in computer vision (CV) tasks but are resource-intensive for edge deployment. Although post-training quantization (PTQ) can help reduce resource demand, its application to hybrid models remains limited. We propose EfficientQuant, a novel structure-aware PTQ approach that applies uniform quantization to convolutional blocks and log2log_2 quantization to transformer blocks. EfficientQuant achieves 2.5×8.7×2.5 \times - 8.7 \times latency reduction with minimal accuracy loss on the ImageNet-1K dataset. It further demonstrates low latency and memory efficiency on edge devices, making it practical for real-world deployment.

Keywords

Cite

@article{arxiv.2506.11093,
  title  = {EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices},
  author = {Shaibal Saha and Lanyu Xu},
  journal= {arXiv preprint arXiv:2506.11093},
  year   = {2025}
}

Comments

Accepted to the 4th Workshop on Transformers for Vision (T4V) at CVPR 2025

R2 v1 2026-07-01T03:14:20.663Z