Xu Gou

About

Xu Gou is a researcher focused on the intersection of deep learning and model efficiency, with a particular emphasis on compressing convolutional neural networks (CNNs) for practical deployment. His most-cited work, "Re-training and parameter sharing with the Hash trick for compressing convolutional neural networks" (2020), introduces a novel approach that combines retraining strategies with hash-based parameter sharing to significantly reduce model size without sacrificing accuracy. This contribution addresses a critical challenge in deploying large-scale CNNs on resource-constrained devices, such as mobile phones and embedded systems. While his citation count of 5 reflects the early stage of his career, the work demonstrates a strong potential for impact in the field of efficient AI. Gou’s research is particularly relevant for students and practitioners seeking to understand how to balance model performance with computational efficiency, offering practical insights into compression techniques that are essential for real-world applications. His ongoing efforts promise to further advance the accessibility and scalability of deep learning models.

Research Focus

Key Achievements

Top Papers

1. 1
   Re-training and parameter sharing with the Hash trick for compressing convolutional neural networks

   5 citations · 2020

Key Collaborators

Contact & Links