DeFRCN icon indicating copy to clipboard operation
DeFRCN copied to clipboard

Published 20 hours ago • verified publisher icon er-muyue

Experimental setting is different from TFA and FSRW

Open 1179021477 opened this issue 2 years ago • 0 comments

In TFA/FSRW, FSOD fine-tune on both base and novel classes, using the same training examples provided by FSRW. And G-FSOD train for multiple runs on different random samples to obtain averages. Can you explain this? The results of only fine-tune on novel classes is not fair to compare with others

1179021477 avatar Jul 11 '22 09:07 1179021477