search

xyupeng / ContrastiveCrop

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning
MIT License
284 stars 27 forks source link

An implementation detail to consult #20

Open 1PSA opened 1 year ago

1PSA commented 1 year ago

You wrote that alpha was set to 0.6 for your method in sec.4.2, while I saw that alpha was set to 0.1 in the config you are given on the github in the folder "small". So I'm wondering which one is used for the results in paper?

xyupeng commented 1 year ago

We use alpha=0.6 for small datasets in the paper. We find in later experiments that alpha=0.1 work slightly better on some small datasets.