In section 4.3 Ablation study and visualization Weight initialization- We explore two different ways of initializing the weights of the novel classifier before few-shot fine-tuning: (1) random initialization and (2) fine-tuning a predictor on the novel set and using the classifier’s weights as initialization. Can you please explain about the (2) here. I didn't understand how classifier weights are used as classifier weights. Thanks in advance
Пікірлер: 1