search

LiJunnan1992 / DivideMix

Code for paper: DivideMix: Learning with Noisy Labels as Semi-supervised Learning
MIT License
529 stars 83 forks source link

Effectiveness of the mixup operation #45

Closed hathawayxxh closed 2 years ago

hathawayxxh commented 2 years ago

Hi Junnan,

Thanks for your excellent work and codes. In the ablation study (Table 5) of your paper, you have conducted the experiments of "DivideMix w/o augmentation". I would like to know what does the augmentation refers to? Does it means the M transformations or the mixup operation? If this augmentation denotes the M transformations, have you ever evaluated the impact of the mixup operation?

Thanks a lot. Xiaohan

LiJunnan1992 commented 2 years ago

Hi Xiaohan, thanks for your question.

The augmentation in Table 5 refers to M transformations. I have not removed mixup because it is an essential piece of the mixmatch operation.

hathawayxxh commented 2 years ago

Thanks for your reply. I will close this issue.