INT and Concept Variance, two embedding-simplicity metrics, improve weighted Kendall's tau by up to 0.32 over state-of-the-art transferability estimators on a new seven-dataset image benchmark.
Each class has 5,000 training samples and 1,000 testing samples
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Occam's model: Selecting simpler representations for better transferability estimation
INT and Concept Variance, two embedding-simplicity metrics, improve weighted Kendall's tau by up to 0.32 over state-of-the-art transferability estimators on a new seven-dataset image benchmark.