Question about experiment in YCB Video dataset
yokies opened this issue · 1 comments
yokies commented
I wonder why there is a different result between 0-shot, 10-shot and 25-shot when use synthetic data(Table2 (a) rows 2 and 3). I think the differnt setting of YCBVtrain has no influence over the synthetic data generation and training progress of detector. Or does the (pre) means that detection model is pre-trained on each few-shot YCBVtrain?
gyhandy commented
Thanks for your question. Yes, (pre) means we use different few-shot images to train the detector before we add the optimization.