The Performance of Transferability Metrics does not Translate to Medical Tasks
Transfer learning boosts the performance of medical image analysis by enabling deep learning (DL) on small datasets through the knowledge acquired from large ones. As the number of DL architectures explodes, exhaustively attempting all candidates becomes unfeasible, motivating cheaper alternatives for choosing them. Transferability scoring methods emerge as an enticing solution, allowing to efficiently calculate a score that correlates with the architecture accuracy on any target dataset. However, since transferability scores have not been evaluated on medical datasets, their use in this context remains uncertain, preventing them from benefiting practitioners. We fill that gap in this work, thoroughly evaluating seven transferability scores in three medical applications, including out-of-distribution scenarios. Despite promising results in general-purpose datasets, our results show that no transferability score can reliably and consistently estimate target performance in medical contexts, inviting further work in that direction.
Code (1)
Tasks
Medical Image AnalysisTransfer LearningSimilar Papers 제목 키워드 기반
On dataset transferability in medical image classification
Current transferability estimation methods designed for natural image datasets are often suboptimal in medical image classification. These methods primarily focus on estimating the suitability of pre-trained source model…
BenchmarkingClassificationimage-classificationImage Classification+1Beyond Attack Success Rate: A Multi-Metric Evaluation of Adversarial Transferability in Medical Imaging Models
While deep learning systems are becoming increasingly prevalent in medical image analysis, their vulnerabilities to adversarial perturbations raise serious concerns for clinical deployment. These vulnerability evaluation…
Adversarial RobustnessEnhancing pretraining efficiency for medical image segmentation via transferability metrics
In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this pro…
Contrastive LearningImage SegmentationMedical Image SegmentationSegmentation+1Transferability Estimation for Semantic Segmentation Task
Transferability estimation is a fundamental problem in transfer learning to predict how good the performance is when transferring a source model (or source task) to a target task. With the guidance of transferability sco…
Autonomous Drivingimage-classificationImage ClassificationMedical Image Analysis+3Topology-Driven Transferability Estimation of Medical Foundation Models for Segmentation
The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medical foundation models for specific segmentation tasks remains a computational …
Self-Supervised Learning