Yu Guoshuai

Papers

Total Citations

H-Index

About

Yu Guoshuai is a researcher whose work sits at the intersection of computer vision and deep learning, with a particular focus on advancing object recognition systems for real-world applications. His key research areas include loss function optimization, efficient neural network architectures, and indoor scene understanding. Guoshuai’s most notable contribution comes from his 2023 paper, "Indoor object recognition based on YOLOv5 with EIOU loss function," which has already garnered 3 citations—a promising start for a focused study. In this work, he tackled a critical challenge in large-scale object classification: the trade-off between training efficiency and model accuracy. By introducing the EIOU (Efficient Intersection over Union) loss function to the YOLOv5 framework, he demonstrated that a well-designed loss function can achieve more precise models with fewer training epochs, directly addressing a bottleneck in practical deployment. This contribution is particularly valuable for resource-constrained environments, such as robotics and smart home systems, where fast and accurate indoor object recognition is essential. Guoshuai’s research highlights the power of incremental algorithmic improvements, and his work serves as a clear example for students and researchers interested in how loss function design can drive performance gains in modern deep learning pipelines.