LogME, aggregated by its minimum per-subset score, best matches fine-tuning accuracy for surgical phase recognition across two datasets, while TransRate reverses true model rankings.
In: 2019 IEEE International Conference on Image Processing (ICIP)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
eess.IV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Analysis of Transferability Estimation Metrics for Surgical Phase Recognition
LogME, aggregated by its minimum per-subset score, best matches fine-tuning accuracy for surgical phase recognition across two datasets, while TransRate reverses true model rankings.