First of all, thank you for sharing this project. It's nice to understand BarlowTwins more with your code.
I've read some unsupervised learning papers like SimCLR and MoCo. The projection there is kind of decreasing the dimension of representations. (2048->512->128, something like this).
On the other hand, BarlowTwins uses the projection layer that increases the dimension of representations. Do you have any thought about the reasons? (I know the loss function and the concept of algorithms are quite different between SimCLR and BarlowTwins but still quite confused about the projection layers)
Look forward to your reply. Again, thank you for this project.
First of all, thank you for sharing this project. It's nice to understand BarlowTwins more with your code. I've read some unsupervised learning papers like SimCLR and MoCo. The projection there is kind of decreasing the dimension of representations. (2048->512->128, something like this). On the other hand, BarlowTwins uses the projection layer that increases the dimension of representations. Do you have any thought about the reasons? (I know the loss function and the concept of algorithms are quite different between SimCLR and BarlowTwins but still quite confused about the projection layers) Look forward to your reply. Again, thank you for this project.