A geometric-mean loss over softmax attention weights improves few-shot classification accuracy over arithmetic-mean losses.
Generalizing from a few examples: A sur- vey on few-shot learning,
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
background 1representative citing papers
citing papers explorer
-
Geometric Mean Improves Loss For Few-Shot Learning
A geometric-mean loss over softmax attention weights improves few-shot classification accuracy over arithmetic-mean losses.