PyRetri
PyRetri copied to clipboard
How to get the same performance as SCDA paper in CUB200-2011 dataset?
How to get the same performance as SCDA paper in CUB200-2011 dataset?
For SCDA, it calculate the top-5 mAP, we calculate mAP on all the samples, so we can not get the same performance.
How to get the same performance as SCDA paper in CUB200-2011 dataset?
Hi,do you get the same performance as SCDA paper in CUB200-2011 dataset by calculating the top-5 mAP?