Yiting Li
Papers
1
Total Citations
3
H-Index
1
About
Yiting Li is an emerging researcher specializing in computer vision and deep learning, with a focused emphasis on few-shot learning and object detection. Their most notable work introduces a Bilateral-Head Region-Based Convolutional Neural Network framework, a unified architecture designed to tackle the challenging problem of incremental few-shot object detection. This contribution addresses a critical gap in practical AI deployment: the ability to continuously learn new object categories from limited labeled examples without forgetting previously acquired knowledge — a capability essential for open-ended, real-world systems. Li's research is particularly motivated by high-stakes applications such as autonomous driving and robotics, domains where acquiring large-scale annotated datasets is often impractical or cost-prohibitive. By bridging incremental learning with few-shot detection, their work pushes the boundaries of what modern detection systems can achieve under constrained supervision. Though still early in their research trajectory, with 3 citations on their 2024 publication, Li's work addresses one of the most pressing scalability challenges in contemporary object detection research. Students and practitioners working on adaptive AI systems, continual learning, or resource-efficient vision models will find Li's contributions a valuable and timely reference point.
Research Focus
Key Achievements
Top Papers
- 1