H
Huixia Li
Researcher at Xiamen University
Publications - 6
Citations - 92
Huixia Li is an academic researcher from Xiamen University. The author has contributed to research in topics: Quantization (signal processing) & Computer science. The author has an hindex of 2, co-authored 4 publications receiving 14 citations.
Papers
More filters
Posted Content
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Huixia Li,Chenqian Yan,Shaohui Lin,Xiawu Zheng,Yuchao Li,Baochang Zhang,Fan Yang,Rongrong Ji +7 more
TL;DR: A new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively and a structured knowledge transfer (SKT) loss is introduced to fine-tune the quantized network.
Journal ArticleDOI
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios
Jiashi Li,Xin Xia,Wei Li,Huixia Li,Xing Wang,Xuefeng Xiao,Ruiqi Rachel Wang,Min Zheng,Xin Pan +8 more
TL;DR: Next-ViT outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks and is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks.
Book ChapterDOI
PAMS: Quantized Super-Resolution via Parameterized Max Scale
TL;DR: Zhang et al. as discussed by the authors proposed a new quantization scheme termed PArameterized Max Scale (PAMS), which applies the trainable truncated parameter to explore the upper bound of the quantization range adaptively.
Journal ArticleDOI
Evolving Fully Automated Machine Learning via Life-Long Knowledge Anchors
Xiawu Zheng,Yang Zhang,Sirui Hong,Huixia Li,Lang Tang,Youcheng Xiong,Jin Zhou,Yan Wang,Xiaoshuai Sun,Pengfei Zhu,Chenglin Wu,Rongrong Ji +11 more
TL;DR: In this paper, the authors present a fully AutoML pipeline to comprehensively automate data preprocessing, feature engineering, model generation/selection/training and ensemble for an arbitrary dataset and evaluation metric.
Journal ArticleDOI
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
Yuexi Ma,Huixia Li,Xiawu Zheng,Xuefeng Xiao,Rui Wang,Shilei Wen,Xin Pan,Fei Chao,Rongrong Ji +8 more
TL;DR: Zhang et al. as discussed by the authors formulated the oscillation in PTQ and proved the problem is caused by the difference in module capacity, where the differentials between adjacent modules are used to measure the degree of oscillation.