Yanyun Qu

Papers

Total Citations

H-Index

About

Yanyun Qu is a leading researcher in computer vision, with a primary focus on object detection and deep learning, particularly in challenging scenarios involving small sample sizes and complex environments. Her most-cited work, "Object Detection Based on Deep Learning of Small Samples" (2018), tackles a critical bottleneck in robotics and indoor scene understanding: the failure of state-of-the-art detectors—trained on massive datasets like PASCAL VOC—when faced with limited labeled data and cluttered backgrounds. This contribution has earned 22 citations, highlighting its relevance to real-world applications such as service robotics. Beyond this, Qu’s broader research advances the robustness of deep learning models under data scarcity, making her a key figure in bridging the gap between large-scale benchmarks and practical deployment. Her work not only addresses fundamental algorithmic challenges but also directly impacts industries requiring reliable vision systems in constrained settings. For students and researchers, Qu exemplifies how targeted innovations in few-shot learning and domain adaptation can drive meaningful progress in applied computer vision.