Unfreezing the patch embedding during low-rank adaptation of a vision transformer yields 96.35% accuracy on encrypted CIFAR-10 with 0.71M trainable parameters.
Rethinking semantic segmentation from a sequence-to-sequence perspective with 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.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification
Unfreezing the patch embedding during low-rank adaptation of a vision transformer yields 96.35% accuracy on encrypted CIFAR-10 with 0.71M trainable parameters.