mlsanityData to 7 Oct 2026

Which Model to Transfer? A Survey on Transferability Estimation

arXiv 2402.15231 ↗First posted 23 Feb 2024cs.LG cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Transfer learning methods endeavor to leverage relevant knowledge from existing source pre-trained models or datasets to solve downstream target tasks. With the increase in the scale and quantity of available pre-trained models nowadays, it becomes critical to assess in advance whether they are suitable for a specific target task. Model transferability estimation is an emerging and growing area of interest, aiming to propose a metric to quantify this suitability without training them individually, which is computationally prohibitive. Despite extensive recent advances already devoted to this area, they have custom terminological definitions and experimental settings. In this survey, we present the first review of existing advances in this area and categorize them into two separate realms: source-free model transferability estimation and source-dependent model transferability estimation. Each category is systematically defined, accompanied by a comprehensive taxonomy. Besides, we address challenges and outline future research directions, intending to provide a comprehensive guide to aid researchers and practitioners.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 49 of its 61 references that are in the map. First posted on arXiv 23 Feb 2024.

Builds on

49 of 61 references.

References · 49

  1. 2020Prevalence of Neural Collapse during the terminal phase of deep learning trainingcited by 713
  2. 2018Taskonomy: Disentangling Task Transfer Learningcited by 631
  3. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  4. 2019Task2Vec: Task Embedding for Meta-Learningcited by 197
  5. 2020LEEP: A New Measure to Evaluate Transferability of Learned Representationscited by 182
  6. 2021LogME: Practical Assessment of Pre-trained Models for Transfer Learningcited by 168
  7. 2022RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rankcited by 145
  8. 2019Transferability and Hardness of Supervised Classification Taskscited by 125
  9. 2016PAC-Bayesian Theory Meets Bayesian Inferencecited by 87
  10. 2019Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learningcited by 86
  11. 2022An Information-Theoretic Approach to Transferability in Task Transfer Learningcited by 79
  12. 2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
37 more
  1. 2021OTCE: A Transferability Metric for Cross-Domain Cross-Task Representationscited by 62
  2. 2022Transferability in Deep Learning: A Surveycited by 57
  3. 2021Transferability Estimation using Bhattacharyya Class Separabilitycited by 53
  4. 2020Ranking Neural Checkpointscited by 50
  5. 2021Frustratingly Easy Transferability Estimationcited by 44
  6. 2014A Weighted Correlation Index for Rankings with Tiescited by 41
  7. 2021A linearized framework and a new benchmark for model selection for fine-tuningcited by 41
  8. 2023Model Spider: Learning to Rank Pre-Trained Models Efficientlycited by 32
  9. 2022PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Taskscited by 30
  10. 2022How stable are Transferability Metrics evaluations?cited by 30
  11. 2022Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Spacecited by 30
  12. 2021Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubscited by 28
  13. 2021Transferability Metrics for Selecting Source Model Ensemblescited by 24
  14. 2020Duality Diagram Similarity: a generic framework for initialization selection in task transfer learningcited by 23
  15. 2023ETran: Energy-Based Transferability Estimationcited by 18
  16. 2023Foundation Model is Efficient Multimodal Multitask Model Selectorcited by 16
  17. 2021Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performancecited by 15
  18. 2020Model Reuse with Reduced Kernel Mean Embedding Specificationcited by 14
  19. 2022Transferability-Guided Cross-Domain Cross-Task Transfer Learningcited by 13
  20. 2023Understanding the Transferability of Representations via Task-Relatednesscited by 11
  21. 2023How to Estimate Model Transferability of Pre-Trained Speech Models?cited by 10
  22. 2023Pick the Best Pre-trained Model: Towards Transferability Estimation for Medical Image Segmentationcited by 10
  23. 2023Exploring Model Transferability through the Lens of Potential Energycited by 10
  24. 2023Fast and Accurate Transferability Measurement by Evaluating Intra-class Feature Variancecited by 9
  25. 2022Evidence > Intuition: Transferability Estimation for Encoder Selectioncited by 7
  26. 2023The Performance of Transferability Metrics does not Translate to Medical Taskscited by 6
  27. 2023Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approachcited by 5
  28. 2023How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Surveycited by 4
  29. 2015Learning to Select Pre-Trained Deep Representations with Bayesian Evidence Frameworkcited by 3
  30. 2021Transferability Estimation for Semantic Segmentation Taskcited by 3
  31. 2022Transferability Estimation Based On Principal Gradient Expectationcited by 3
  32. 2020Ranking and Rejecting of Pre-Trained Deep Neural Networks in Transfer Learning based on Separation Indexcited by 2
  33. 2022Model Selection, Adaptation, and Combination for Transfer Learning in Wind and Photovoltaic Power Forecastscited by 2
  34. 2023Transferability Metrics for Object Detectioncited by 2
  35. 2021Practical Transferability Estimation for Image Classification Taskscited by 1
  36. 2023To transfer or not transfer: Unified transferability metric and analysiscited by 1
  37. 2023Unleashing the power of Neural Collapse for Transferability Estimationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 7; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024Assessing Pre-Trained Models for Transfer Learning Through Distribution of Spectral Componentscited by 6
  2. 2025Understanding Knowledge Transferability for Transfer Learning: A Surveycited by 4
  3. 2024Beyond Knowledge Silos: Task Fingerprinting for Democratization of Medical Imaging AIcited by 2
  4. 2024Know2Vec: A Black-Box Proxy for Neural Network Retrievalcited by 2
  5. 2025Estimating Time Series Foundation Model Transferability via In-Context Learningcited by 2
  6. 2025How NOT to benchmark your SITE metric: Beyond Static Leaderboards and Towards Realistic Evaluationcited by 2
  7. 2024The Inter-Intra Modal Measure: A Predictive Lens on Fine-Tuning Outcomes in Vision-Language Modelscited by 1
  8. 2024Learning to Rank Pre-trained Vision-Language Models for Downstream Taskscited by 1
  9. 2025Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddingscited by 1
  10. 2025Unsupervised Source-Free Ranking of Biomedical Segmentation Models Under Distribution Shiftcited by 0
  11. 2025Learning Optimal Prompt Ensemble for Multi-source Visual Prompt Transfercited by 0
  12. 2025MetaRank: Task-Aware Metric Selection for Model Transferability Estimationcited by 0
1 more
  1. 2026Model Specific Task Similarity for Vision Language Model Selection via Layer Conductancecited by 0