S2FT replaces the sparse-spectrum assumption of prior Fourier PEFT with a learned rearrangement that maps a pre-estimated weight change into a domain where few spectral coefficients suffice.
Zookt: Task-adaptive knowledge transfer of model zoo for few-shot learning.Pattern Recogni- tion, 158:110960
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
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
S2FT replaces the sparse-spectrum assumption of prior Fourier PEFT with a learned rearrangement that maps a pre-estimated weight change into a domain where few spectral coefficients suffice.