AOFT generates approximately orthogonal down/up projection matrices from a single learnable vector, matching the observed near-orthogonality of pre-trained ViT weights, and reports competitive image-classification performance with fewer tunable parameters.
Matrix computa- tions
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy
AOFT generates approximately orthogonal down/up projection matrices from a single learnable vector, matching the observed near-orthogonality of pre-trained ViT weights, and reports competitive image-classification performance with fewer tunable parameters.