What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has become the de-facto approach, despite differences in the tasks and im-age characteristics between the domains. However, it is un-clear what factors determine whether - and to what extent- transfer learning to the medical domain is useful. The long- standing assumption that features from the source domain get reused has recently been called into question. Through a series of experiments on several medical image bench-mark datasets, we explore the relationship between transfer learning, data size, the capacity and inductive bias of the model, as well as the distance between the source and tar-get domain. Our findings suggest that transfer learning is beneficial in most cases, and we characterize the important role feature reuse plays in its success.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
How transferable are features in deep neural networks?
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014) · arXiv · doi:10.48550/arxiv.1411.1792 · Cited by 6,061 · cited 2×
“[43] found early features tend to be more general, and as we move deeper into the network the features become more task-specific.”
BackgroundEmerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 2×
“This fits with previous works that have shown that local attention, which is crucial for good performance, is learned in early layers [7, 11].”
MethodResult
Cited by
Benchmarking Self-Supervised Learning on Diverse Pathology Datasets
Kang, M., Song, H., Park, S., Yoo, D., & Pereira, S. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00326 · Cited by 187
A systematic review of intermediate fusion in multimodal deep learning for biomedical applications
Guarrasi, V., Aksu, F., Caruso, C. M., Di Feola, F., Rofena, A., Ruffini, F., & Soda, P. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105509 · Cited by 95
Assessing the limits of zero-shot foundation models in single-cell biology
Kedzierska, K. Z., Crawford, L., Amini, A. P., & Lu, A. X. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.16.561085 · Cited by 61
Feature Reuse and Scaling: Understanding Transfer Learning with Protein Language Models
Li, F.-Z., Amini, A. P., Yue, Y., Yang, K. K., & Lu, A. X. (2024) · doi:10.1101/2024.02.05.578959 · Cited by 51
Pre-training in Medical Data: A Survey
Qiu, Y., Lin, F., Chen, W., & Xu, M. (2023) · Machine Intelligence Research · doi:10.1007/s11633-022-1382-8 · Cited by 30
Promise: Prompt-Driven 3D Medical Image Segmentation Using Pretrained Image Foundation Models
Li, H., Liu, H., Hu, D., Wang, J., & Oguz, I. (2024) · 2024 IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635207 · Cited by 29
Li, H., Liu, H., Hu, D., Wang, J., & Oguz, I. (2024) · 2024 IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635343 · Cited by 9
Scaling Laws for Galaxy Images
Walmsley, M., Bowles, M., Scaife, A. M. M., Makechemu, J. S., Gordon, A. J., Ferguson, A. M. N., Mann, R. G., Pearson, J., Popp, J. J., Bovy, J., et al. (2024) · arXiv · doi:10.48550/arxiv.2404.02973 · Cited by 2
“The medical imaging community, which shares a need for label-efficient adaption to qualitatively different images, ‘routinely’ [12] applies ImageNet-like pretraining with varying results [13, 14, 15, 16].”
Background
Metadata
- Authors
- Matsoukas, C., Haslum, J. F., Sorkhei, M., Soderberg, M., & Smith, K.
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 9215-9224
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312713789
- Cited by
- 113
- References
- 22
- FWCI
- 14.38
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.