SSKD

2000년 도입 · 논문 1편에서 사용

Semi-Supervised Knowledge Distillation is a type of knowledge distillation for person re-identification that exploits weakly annotated data by assigning soft pseudo labels to YouTube-Human to improve models' generalization ability. SSKD first trains a student model (e.g. ResNet-50) and a teacher model (e.g. ResNet-101) using labeled data from multi-source domain datasets. Then, SSKD develops an auxiliary classifier to imitate the soft predictions of unlabeled data generated by the teacher model. Meanwhile, the student model is also supervised by hard labels and predicted soft labels by the teacher model for labeled data.

출처: Semi-Supervised Domain Generalizable Person Re-Identification

소개 논문: Semi-Supervised Domain Generalizable Person Re-Identification