Hello authors! thanks for releasing your awesome works with the clear paper and appendix!
I could not find any mention of data augmentation in the paper, appendix, or code. Could you clarify the rationale?
Was data augmentation intentionally excluded to isolate the contribution of the missing modality bank and the G-router / S-router training strategy, or did you observe degradation when trying augmentation?
Or are there specific modules that are particularly sensitive to augmentation? (Missing modality bank, S-router specialization with top-1 gating, G-router generalization, and so on...)
Thank you!
Hello authors! thanks for releasing your awesome works with the clear paper and appendix!
I could not find any mention of data augmentation in the paper, appendix, or code. Could you clarify the rationale?
Was data augmentation intentionally excluded to isolate the contribution of the missing modality bank and the G-router / S-router training strategy, or did you observe degradation when trying augmentation?
Or are there specific modules that are particularly sensitive to augmentation? (Missing modality bank, S-router specialization with top-1 gating, G-router generalization, and so on...)
Thank you!