search

LiheYoung / UniMatch

[CVPR 2023] Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation
https://arxiv.org/abs/2208.09910
MIT License
478 stars 60 forks source link

Question for CutMix #34

Closed kevinshieh0225 closed 1 year ago

kevinshieh0225 commented 1 year ago

Hi, thanks for the great work!

I have found that you used additional dataloader for the cutmix sources.

Since most of the work will mix by using the image from the same loaded batches, I was wondering what is the intention of using mixing sources from another batch, and will it affect the training result by using the common setting which only using one dataloader and the same batch for mixing? Thanks!

LiheYoung commented 1 year ago

Actually, it is not an intentional practice. We later found that we can simply CutMix an image batch with its shuffled version. The performance will not be affected.

kevinshieh0225 commented 1 year ago

That is great! It will be easier to implement if so!