Zhiqiu Xu / 徐之秋 / Oscar

I am a Ph.D. student at University of Pennsylvania, advised by Prof. Mayur Naik. I seek to understand how neural networks work and develop simple methods to improve neural network training.

I complete my Master of Science degree from UC Berkeley, advised by Prof. Trevor Darrell , where I work on computer vision and representation learning.

Before that, I was an undergraduate student at UC Berkeley, majoring in Computer Science and Applied Mathematics. I also interned at Twitter.

I was closely mentored by Dr. Zhuang Liu and Ph.D. candidate Ruiqi Zhong at UC Berkeley. They are primarily reasons why I dived into research. That is also why I am open to mentoring junior students on research. See Mentorship section.

Email  /  Google Scholar  /  Twitter  /  Github  /  Wechat

• (2024/01/16) Our paper Initializing Models with Larger Ones is accepted to ICLR 2024 as a spotlight presentation! Happy birthday to me 🎂
• (2023/04/24) Our paper Dropout Reduces Underfitting is accepted to ICML 2023!
• (2023/03/31) I will join University of Pennsylvania as a Ph.D. student in Fall 2023!

We introduce weight selection, a method for initializing models by selecting a subset of weights from a pretrained larger model. With no extra cost, it is effective for improving the accuracy of a smaller model and reducing its training time needed to reach a certain accuracy level.

We propose early dropout and late dropout. Early dropout helps underfitting models fit the data better and achieve lower training loss. Late dropout helps improve the generalization performance of overfitting models.

In this work, we demonstrate the potential of SVRG in optimizing real-world neural networks. we introduce a multiplicative coefficient α to control the strength and adjust it through a linear decay schedule. We name our method α-SVRG.

Our full method, named Anytime Dense Prediction with Confidence (ADP-C), achieves the same level of final accuracy with HRNet-w48, and meanwhile significantly reduces total computation.

Just like every other field in human society, the flourishing academic community is reliant on passing the torch of knowledge. If you are interested in my research and deep learning related topics and want to chat with me, please don't hesitate to reach out. Here is a list of students I have mentored. One of them said I was a legendary mentor, and let's trust his judgement for this time.

Reviewer for ICCV, NeurIPS, CVPR, ECCV.

• My Chinese name is pronounced as Shoe-Jee-Chyo. I will be very happy if you try to pronounce that in front of me.
• Occasionally, I post some vlogs on bilibili. Here's my homepage.
• My profile photo is shot in a studio, I never dress like that in real life.
• I proudly named myself as Oscar after watching Shark Tale at 6 years old.

Website design from Jon Barron Borrowed from Ruiqi Zhong