About Accuracy

[Ien001]

hi,
I`m working on reimplementing "Learning a Discriminative Filter Bank Within a CNN for Fine-Grained Recognition" now, but I cannot get the result in the paper, do you get the same accuracy listed in the paper?

Ian

[mengrang]

Do you implement the layers nonrandomly initiallation?it makes the key role in the accuracy

[Ien001]

Yeah.. but it seems like I'm failed on it, the accuracy is no different after I finish nonrandomly initiallation.
Many ppl said that there are some tricks in the paper😳, I don't know, maybe I did sth wrong.

[mengrang]

Thanks for your comments, I am also intersted in the initialltion works.You can click here for My understanding of the initiallztion.

[fxle]

@Ien001 How do you try to nonrandomly initiallation?Can you share you idea? Thank you

[fxle]

@mengrang How accurate are you getting? In addition，Where to get these two files?'AgriculturalDisease_train_annotations.json'',"AgriculturalDisease_validation_annotations.json"

[mengrang]

The acc on my dataset is just OK, the two json files is my dataset

[Ien001]

Hi, I have read it, @mengrang
it seems okay,
have u implement ur idea?

[doublemanyu]

Have you implement the non-random initialization? @mengrang @Ien001 @fxle

[chaerlo]

@Ien001 what‘s the accuracy u implement the non-random initialization？