about ViT performance on EEG data about eeg-transformer HOT 3 OPEN

Thanks for your interests in my course project. This project was started in 2022 and I feel it's a bit outdated (and I'm no longer maintaining it because I don't do research in the EEG domain).

My suggestion would simply be to give up the classical ViT architecture but try the following:

(1) Finetuning from an autoregressive ViT that predict both patches and labels. This gives you more training signals given limited data. You can use a LoRA and/or an adaptor to make training efficient and/or accommodate your input/output.
(2) Try SSSMs such as Mamba.

from eeg-transformer.

Thanks for your advice! I have tried to simply replace mamba into aformentioned conformer, but it even get worse.
I did another domain generalization experiment on EEG, and I simply changed the depth of transformer block, and it reached the SOTA performance!

from eeg-transformer.

Thanks for your advice! I have tried to simply replace mamba into aformentioned conformer, but it even get worse. I did another domain generalization experiment on EEG, and I simply changed the depth of transformer block, and it reached the SOTA performance!

Hi DrugLover,
I'm recently working on a similar project, aiming to do an SSL pertaining on EEG data from various sources and later fine-tuning on the downstream classification task using transformer-based models. My experiments also showed that most time these large models did not perform as well as small models (e.g., eegnet). I am wondering if we could have a discussion somewhere on this matter, maybe we can do something together. You can reach me through the following email: [email protected]. I'm looking forward to hearing from you soon.

from eeg-transformer.