Showing cs.CVShow all
2 papers · 1 filter
cs.CV2024
Progressive Fine-to-Coarse Reconstruction for Accurate Low-Bit Post-Training Quantization in Vision Transformers
Rui Ding, Liang Yong, Sihuan Zhao +4
Due to its efficiency, Post-Training Quantization (PTQ) has been widely adopted for compressing Vision Transformers (ViTs). However, when quantized into low-bit representations, th…
cs.CV2024
PSE-Net: Channel Pruning for Convolutional Neural Networks with Parallel-subnets Estimator
Shiguang Wang, Tao Xie, Haijun Liu +2
Channel Pruning is one of the most widespread techniques used to compress deep neural networks while maintaining their performances. Currently, a typical pruning algorithm leverage…