At the same time, I have a question about few-shot-object-detection task, if it is based on fine-tuning, can the pre-training model include base-classes? For example, fine-tune by VOC(1-5shot) and Val on VOC(20 classes), but pretrained on Coco 2017(80 classes above voc 20classes). I am looking forward to your reply.
At the same time, I have a question about few-shot-object-detection task, if it is based on fine-tuning, can the pre-training model include base-classes? For example, fine-tune by VOC(1-5shot) and Val on VOC(20 classes), but pretrained on Coco 2017(80 classes above voc 20classes). I am looking forward to your reply.