Empirical tests show adapters (2-3 per block) and LoRA on deformable attention achieve competitive instance segmentation with 1-6% parameters tuned versus 40-55% for full fine-tuning.
SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules.arXiv2024, arxiv:2403.11887
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks
Empirical tests show adapters (2-3 per block) and LoRA on deformable attention achieve competitive instance segmentation with 1-6% parameters tuned versus 40-55% for full fine-tuning.