Q-HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction

no code implementations • 22 Mar 2023 • Jemin Lee, Yongin Kwon, Jeman Park, Misun Yu, Sihyeong Park, Hwanjun Song

To overcome these challenges, we propose a new post-training quantization method, which is the first to quantize efficient hybrid ViTs (MobileViTv1, MobileViTv2, Mobile-Former, EfficientFormerV1, EfficientFormerV2) with a significant margin (an average improvement of 8. 32\% for 8-bit and 26. 02\% for 6-bit) compared to existing PTQ methods (EasyQuant, FQ-ViT, and PTQ4ViT).

Quantization

On the Performance of Generative Adversarial Network (GAN) Variants: A Clinical Data Study

no code implementations • 21 Sep 2020 • Jaesung Yoo, Jeman Park, An Wang, David Mohaisen, Joongheon Kim

Generative Adversarial Network (GAN) is a useful type of Neural Networks in various types of applications including generative models and feature extraction.

Generative Adversarial Network

Examining Adversarial Learning against Graph-based IoT Malware Detection Systems

no code implementations • 12 Feb 2019 • Ahmed Abusnaina, Aminollah Khormali, Hisham Alasmary, Jeman Park, Afsah Anwar, Ulku Meteriz, Aziz Mohaisen

The main goal of this study is to investigate the robustness of graph-based Deep Learning (DL) models used for Internet of Things (IoT) malware classification against Adversarial Learning (AL).

Adversarial Attack General Classification +2