LearningToCountEverything icon indicating copy to clipboard operation
LearningToCountEverything copied to clipboard

Published 20 hours ago • verified publisher icon cvlab-stonybrook

Experiments on CARPK

Open zyweven opened this issue 2 years ago • 2 comments

Hello I use the pre-trained model provided by you to conduct shot-3 experiments on CARPK, and the result is MAE: 43.02, RMSE: 58.12. Is this normal? How many examples are used in the CARPK experiment in the paper?

zyweven avatar Oct 29 '22 14:10 zyweven

Hey, the CARPK result mentioned in the paper uses 12 exemplars(as mentioned in the paper). We randomly sample 12 exemplars from different training images, and use this fixed set of exemplars for the evaluation. Also, we do not do the test time adaption for the pertained model. I don't recall the exact 3-shot results, but it was definitely worse than the 12-shot result.

Viresh-R avatar Oct 30 '22 01:10 Viresh-R

@Viresh-R Could you please release the train and inference code for CARPK?

donggoing avatar Nov 28 '23 06:11 donggoing