GSAM applies random cropping to enable variable input sizes for efficient SAM fine-tuning, claiming lower compute with comparable or higher accuracy on varied datasets.
Pattern recognition letters30(2), 88–97 (2009)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalized SAM: Efficient Fine-Tuning of SAM for Variable Input Image Sizes
GSAM applies random cropping to enable variable input sizes for efficient SAM fine-tuning, claiming lower compute with comparable or higher accuracy on varied datasets.