Showing eess.IVShow all
2 papers · 1 filter
eess.IV2024
LATTE: Low-Precision Approximate Attention with Head-wise Trainable Threshold for Efficient Transformer
Jiing-Ping Wang, Ming-Guang Lin, An-Yeu +1
With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the mode…
eess.IV2023
TSPTQ-ViT: Two-scaled post-training quantization for vision transformer
Yu-Shan Tai, Ming-Guang Lin, An-Yeu +1
Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on…