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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Estimate transferability with TransRate, the difference between feature coding rate overall and within labels | ResNet-18 source-model selection · CIFAR-100 | Pearson correlation (R_p): 0.5330 -> 0.7262 | Improved |
| Estimate transferability with TransRate, the difference between feature coding rate overall and within labels | ResNet-18 source-model selection · FMNIST | Pearson correlation (R_p): 0.7248 -> 0.8614 | Improved |
| Use TransRate to score candidate transferred layers | ResNet-20 pretrained on SVHN · CIFAR-100 layer selection | Pearson correlation (R_p): -0.1895 -> 0.9769 | Improved |
| Use TransRate to score candidate transferred layers | ResNet-18 pretrained on Birdsnap · CIFAR-100 layer selection | Pearson correlation (R_p): 0.7003 -> 0.9871 | Improved |
| Estimate transferability with TransRate | Transferability estimation across target-sample sizes · FMNIST source selection | Kendall's tau and weighted Kendall's tau | Improved |
| Vary epsilon below the reported threshold | TransRate · Transferability estimation | Transferability-estimation performance | No 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.
- LEEP — LEEP: A New Measure to Evaluate Transferability of Learned Representations (ICML 2020) · better on 1 of 1 shared result
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
- Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance (ICCV 2023 · similarity 0.90)
- Understanding the Transferability of Representations via Task-Relatedness (NeurIPS 2024 · similarity 0.88)
- A Mathematical Framework for Quantifying Transferability in Multi-source Transfer Learning (NeurIPS 2021 · similarity 0.87)
- Implicit Modeling for Transferability Estimation of Vision Foundation Models (NeurIPS 2025 · similarity 0.86)
- Features are fate: a theory of transfer learning in high-dimensional regression (ICML 2025 · similarity 0.86)
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning (NeurIPS 2025 · similarity 0.84)
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.
