AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Frustratingly Easy Transferability Estimation

Long-Kai Huang, Junzhou Huang, Yu Rong, Qiang Yang, Ying Wei

ICML 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Estimate transferability with TransRate, the difference between feature coding rate overall and within labelsResNet-18 source-model selection · CIFAR-100Pearson correlation (R_p): 0.5330 -> 0.7262Improved
Estimate transferability with TransRate, the difference between feature coding rate overall and within labelsResNet-18 source-model selection · FMNISTPearson correlation (R_p): 0.7248 -> 0.8614Improved
Use TransRate to score candidate transferred layersResNet-20 pretrained on SVHN · CIFAR-100 layer selectionPearson correlation (R_p): -0.1895 -> 0.9769Improved
Use TransRate to score candidate transferred layersResNet-18 pretrained on Birdsnap · CIFAR-100 layer selectionPearson correlation (R_p): 0.7003 -> 0.9871Improved
Estimate transferability with TransRateTransferability estimation across target-sample sizes · FMNIST source selectionKendall's tau and weighted Kendall's tauImproved
Vary epsilon below the reported thresholdTransRate · Transferability estimationTransferability-estimation performanceNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy