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).
no code implementations • 10 Feb 2022 • Jemin Lee, Misun Yu, Yongin Kwon, TaeHo Kim
To adopt convolutional neural networks (CNN) for a range of resource-constrained targets, it is necessary to compress the CNN models by performing quantization, whereby precision representation is converted to a lower bit representation.