DiTASK fine-tunes vision transformers for multiple tasks by applying learnable diffeomorphic maps to the singular values of frozen weights, and reports state-of-the-art multi-task performance with fewer parameters.
Transformers learn through gradual rank increase
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
unclear 1representative citing papers
citing papers explorer
-
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations
DiTASK fine-tunes vision transformers for multiple tasks by applying learnable diffeomorphic maps to the singular values of frozen weights, and reports state-of-the-art multi-task performance with fewer parameters.