Meta-learning over dataset features and learning curves lets QTT-SEG find SAM fine-tuning configurations that beat zero-shot and a strong AutoML baseline in under three minutes.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Quickly Tuning Foundation Models for Image Segmentation
Meta-learning over dataset features and learning curves lets QTT-SEG find SAM fine-tuning configurations that beat zero-shot and a strong AutoML baseline in under three minutes.