Zhiwen Cao

Mr. Zhiwen Cao

Purdue University West Lafayette, West Lafayette, Indiana, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

27 May 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Yubo ShaoYubo Shao
Yubo Shao
YZYouming Zhao
Youming Zhao
ZCZhiwen Cao
Zhiwen Cao
ZPZhehao Peng
Zhehao Peng
XPXingang Peng
Xingang Peng
AMand Ma
and Ma
It is hard to directly deploy deep learning models on today’s smartphones due to the substantial computational costs introduced by millions of parameters. To compress the model, we develop an ℓ0-based sparse group lasso model called MobilePrune which can generate extremely compact neural network models for both desktop and mobile platforms. We adopt group lasso penalty to enforce sparsity at the group level to benefit General Matrix Multiply (GEMM) and develop the very first algorithm that can optimize the ℓ0 norm in an exact manner and achieve the global convergence guarantee in the deep learning context. MobilePrune also allows complicated group structures to be applied on the group penalty (i.e., trees and overlapping groups) to suit DNN models with more complex architectures. Empirically, we observe the substantial reduction of compression ratio and computational costs for various popular deep learning models on multiple benchmark datasets compared to the state-of-the-art methods. More importantly, the compression models are deployed on the android system to confirm that our approach is able to achieve less response delay and battery consumption on mobile phones.

25 July 2023 in arXiv
Verified
Preprint
Open access
PDF file
CHCheng Han
Cheng Han
QWQifan Wang
Qifan Wang
YCYiming Cui
Yiming Cui
ZCZhiwen Cao
Zhiwen Cao
Wenguan WangWenguan Wang
Wenguan Wang
Dongfang LiuDongfang Liu
Dongfang Liu
As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the number of tunable parameters during fine-tuning. Although these methods show promising results, there is still a significant performance gap compared to full fine-tuning. To address this challenge, we propose an Effective and Efficient Visual Prompt Tuning (E^2VPT) approach for large-scale transformer-based model adaptation. Specifically, we introduce a set of learnable key-value prompts and visual prompts into self-attention and input layers, respectively, to improve the effectiveness of model fine-tuning. Moreover, we design a prompt pruning procedure to systematically prune low importance prompts while preserving model performance, which largely enhances the model's efficiency. Empirical results demonstrate that our approach outperforms several state-of-the-art baselines on two benchmarks, with considerably low parameter usage (e.g., 0.32% of model parameters on VTAB-1k). Our code is available at https://github.com/ChengHan111/E2VPT.