Weifeng Lin (林炜丰)

I am a third year Master student at South China University of Technology, advised by Prof. Lianwen Jin. I received my Bachelor degree also from South China University of Technology in 2021, where I spent a wonderful four years.

My research interests encompass a variety of exciting areas, including Computer Vision (CV), Multi-Models and Generative models. I'm deeply committed to contributing to open source projects, as I firmly believe that constitute a cornerstone for the sustainable growth of the AI commuunity.

Email: wflin37@gmail.com  /  Google Scholar  /  Github

profile photo
Research
Hierarchical Side-Tuning for Vision Transformers
Weifeng Lin, Ziheng Wu, Jiayu Chen, Wentao Yang, Mingxin Huang, Jun Huang, Lianwen Jin,
arxiv, 2023
[paper] [Code]

Parameter-efficient transfer learning for vision Transformers in various vision tasks (classification, detection, segmentation)

Scale-Aware Modulation Meet Transformer
Weifeng Lin, Ziheng Wu, Jiayu Chen, Jun Huang, Lianwen Jin,
International Conference on Computer Vision (ICCV), 2023
[paper] [Code]

Hybrid CNN-Transformer Network (Vision Transformer Backbone)

Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed
Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Ziheng Wu, Zipeng Zhang, Kui Jia, Lianwen Jin, Cen Chen Jun Huang
Annual Meeting of the Association for Computational Linguistics (ACL-Industry), 2023
[paper]

Rapid Diffusion is a novel framework for training and deploying superresolution, text-to-image latent diffusion models with rich entity knowledge injected and optimized networks.

Building A Mobile Text Recognizer via Truncated SVD-based Knowledge Distillation-Guided NAS
Weifeng Lin, Canyu Xie, Dezhi Peng, Jiapeng Wang, Lianwen Jin, Wei Ding, Lianwen Jin, Cong Yao Mengchao He
British Machine Vision Conference (BMVC), 2023
[paper] [Detection] [Recognition] [Demo]

We propose a mobile text recognizer that integrates Truncated Singular Value Decomposition (TSVD)-based Knowledge Distillation (KD) into the Neural Architecture Search (NAS) process

Internship
Alibaba Cloud

Research Intern, Machine Learning - Deep Learning Algorithms.


template adapted from this awesome website