Fine-Grained Prototypes Distillation for Few-Shot Object Detection

1 code implementation • 15 Jan 2024 • Zichen Wang, Bo Yang, Haonan Yue, Zhenghao Ma

However, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance. New methods are required to capture the distinctive local context for more robust novel object detection.

Few-Shot Object Detection Meta-Learning +3