search

yformer / EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Apache License 2.0
1.97k stars 142 forks source link

Datasets used in pretraining #23

Open Cbtor opened 6 months ago

Cbtor commented 6 months ago

In Section 4.1, it seems that only IN1K is used for pretraining. But in Table 1, both SA-1b and IN1K are used in pretraining. Which is the correct one?

yformer commented 6 months ago

@Cbtor, only ImageNet1K is used in pretraining. SA-1B is just for getting original SAM model and it will be not be used during pretraining. Since original SAM model is needed during pretraining, I also add the dataset SA-1B in Table 1 to indicate the need for original SAM model.