Masking 75% of image patches during client-side training and moving deep layers to the server yields faster, cheaper federated ViT training with modest accuracy gains.
Dearkd: data-efficient early knowledge distillation for vision transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients
Masking 75% of image patches during client-side training and moving deep layers to the server yields faster, cheaper federated ViT training with modest accuracy gains.