# Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variance

arXiv: https://arxiv.org/abs/2308.05986 · HTML: https://mlsanity.com/paper/2308.05986/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 11 Aug 2023.

## Builds on (most cited first, 16 of 16)

- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning](https://mlsanity.com/paper/1904.06627/) (2019)
- [Task2Vec: Task Embedding for Meta-Learning](https://mlsanity.com/paper/1902.03545/) (2019)
- [LEEP: A New Measure to Evaluate Transferability of Learned Representations](https://mlsanity.com/paper/2002.12462/) (2020)
- [LogME: Practical Assessment of Pre-trained Models for Transfer Learning](https://mlsanity.com/paper/2102.11005/) (2021)
- [Transferability and Hardness of Supervised Classification Tasks](https://mlsanity.com/paper/1908.08142/) (2019)
- [A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses](https://mlsanity.com/paper/2003.08983/) (2020)
- [An Information-Theoretic Approach to Transferability in Task Transfer Learning](https://mlsanity.com/paper/2212.10082/) (2022)
- [Improving Generalization via Scalable Neighborhood Component Analysis](https://mlsanity.com/paper/1808.04699/) (2018)
- [DINE: Domain Adaptation from Single and Multiple Black-box Predictors](https://mlsanity.com/paper/2104.01539/) (2021)
- [Frustratingly Easy Transferability Estimation](https://mlsanity.com/paper/2106.09362/) (2021)
- [Unsupervised Domain Adaptation of Black-Box Source Models](https://mlsanity.com/paper/2101.02839/) (2021)
- [Multi-Source Unsupervised Domain Adaptation via Pseudo Target Domain](https://mlsanity.com/paper/2202.10725/) (2022)
- [Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2206.07551/) (2022)
- [Heterogeneous domain adaptation: An unsupervised approach](https://mlsanity.com/paper/1701.02511/) (2017)

## Built on by (most cited first, 9 of 9)

- [Which Model to Transfer? A Survey on Transferability Estimation](https://mlsanity.com/paper/2402.15231/) (2024)
- [Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Components](https://mlsanity.com/paper/2412.19085/) (2024)
- [Sequence Transferability and Task Order Selection in Continual Learning](https://mlsanity.com/paper/2502.06544/) (2025)
- [Exploring Structural Degradation in Dense Representations for Self-supervised Learning](https://mlsanity.com/paper/2510.17299/) (2025)
- [Understanding Knowledge Transferability for Transfer Learning: A Survey](https://mlsanity.com/paper/2507.03175/) (2025)
- [k-NN as a Simple and Effective Estimator of Transferability](https://mlsanity.com/paper/2503.18528/) (2025)
- [Back to the Basics on Predicting Transfer Performance](https://mlsanity.com/paper/2405.20420/) (2024)
- [Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking](https://mlsanity.com/paper/2409.16198/) (2024)
- [Multi-source Transfer Learning of Time Series with a Shapelet-based Distance Measure](https://mlsanity.com/paper/2609.15148/) (2026)

## Abstract (arXiv)

Given a set of pre-trained models, how can we quickly and accurately find the most useful pre-trained model for a downstream task? Transferability measurement is to quantify how transferable is a pre-trained model learned on a source task to a target task. It is used for quickly ranking pre-trained models for a given task and thus becomes a crucial step for transfer learning. Existing methods measure transferability as the discrimination ability of a source model for a target data before transfer learning, which cannot accurately estimate the fine-tuning performance. Some of them restrict the application of transferability measurement in selecting the best supervised pre-trained models that have classifiers. It is important to have a general method for measuring transferability that can be applied in a variety of situations, such as selecting the best self-supervised pre-trained models that do not have classifiers, and selecting the best transferring layer for a target task. In this work, we propose TMI (TRANSFERABILITY MEASUREMENT WITH INTRA-CLASS FEATURE VARIANCE), a fast and accurate algorithm to measure transferability. We view transferability as the generalization of a pre-trained model on a target task by measuring intra-class feature variance. Intra-class variance evaluates the adaptability of the model to a new task, which measures how transferable the model is. Compared to previous studies that estimate how discriminative the models are, intra-class variance is more accurate than those as it does not require an optimal feature extractor and classifier. Extensive experiments on real-world datasets show that TMI outperforms competitors for selecting the top-5 best models, and exhibits consistently better correlation in 13 out of 17 cases.