2 papers
cs.CV2023
Holistic Prototype Attention Network for Few-Shot VOS
Yin Tang, Tao Chen, Xiruo Jiang +3
Few-shot video object segmentation (FSVOS) aims to segment dynamic objects of unseen classes by resorting to a small set of support images that contain pixel-level object annotatio…
cs.CV2023
AMD: Adaptive Masked Distillation for Object Detection
Guang Yang, Yin Tang, Jun Li +2
As a general model compression paradigm, feature-based knowledge distillation allows the student model to learn expressive features from the teacher counterpart. In this paper, we…