coil fixed memory about pycil HOT 8 CLOSED

Thanks for your interest.

The results of iCaRL in Table 1 are reproduced with BCE loss, following the official implementation.

When preparing the toolbox, we try different parameter combination and loss terms, and switch the BCE loss with CE loss. It turns out our choice helps to improve the performance of iCaRL.

Feel free to reopen it if you have more questions.

from pycil.

sorry to bother you again, in your cub200 or cub100 setting, did you use the pretrain imagenet resnet18?

I did the exemperiment over cub dataset, but my results is very poor.

I checked the paper link, I found they used the pretrained model to finetune for class-incremental learning.

from pycil.

Yes, pretrain is needed for CUB.

from pycil.

Hi,

I achevied the similar results of ur coil on CUB200 according to Figure 4(h) in the first 4 tasks. (I tried the Fixed Total Memory Setting, as most equally class incremental methods use this protocol)

In your paper:

Correspondingly, we also conduct the experiment on CUB-100/200 with rare exemplars, i.e., we only save three exemplars per class.

Fixed Total Memory Setting:

Does it mean that I save 600 (200 * 3) samples in total and then as the task increases, the number of samples per class decreases. For example, 30(600/20) exemplers per class in 2nd task; 15(600/40) exemplers per class in 2nd task; And finally, 3 imgs per classes?

Fixed imgs per class Memory Setting:

Or just fixed the memory 3 imgs per classes from the begining.

What exactly is your replay memory method (Fixed total memory?)

Thx in advance.

from pycil.

Hi, maybe you should read iCaRL [1] first, where you can build the basic idea of exemplars. Our implementation is based on it, see here.

[1] iCaRL: Incremental Classifier and Representation Learning

from pycil.

Thx for your quick replay, my issue seems unclear.

Sry.

I just wanna check your CUB200 experiment settings.

#2 (comment)

memory_size or memory_per_class? (600 in total or 3 per classes)

Following up on the link you provided, it should be "memory_size" (CIFAR100 settings)

https://github.com/zhoudw-zdw/MM21-Coil/blob/f4ebcc15cb21126c1367d4481d25e8ed0689e20f/models/COIL.py#L102

from pycil.

Should be the former one.

from pycil.

Thank you for your patient explanation.

Have a good day!

from pycil.