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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Saha, Shaibal, Xu, Lanyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909647325102080
author Saha, Shaibal
Xu, Lanyu
author_facet Saha, Shaibal
Xu, Lanyu
contents 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 $log_2$ quantization to transformer blocks. EfficientQuant achieves $2.5 \times - 8.7 \times$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices
Saha, Shaibal
Xu, Lanyu
Computer Vision and Pattern Recognition
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 $log_2$ quantization to transformer blocks. EfficientQuant achieves $2.5 \times - 8.7 \times$ 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.
title EfficientQuant: An Efficient Post-Training Quantization for CNN-Transformer Hybrid Models on Edge Devices
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.11093