Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918524258091008 |
|---|---|
| author | Lu, Yucheng Zając, Hubert Dariusz Cheplygina, Veronika Jiménez-Sánchez, Amelia |
| author_facet | Lu, Yucheng Zając, Hubert Dariusz Cheplygina, Veronika Jiménez-Sánchez, Amelia |
| contents | Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic principles, which can impact the generalizability of algorithms and, thus, patient outcomes. This study investigates these decisions through a task-based survey with machine learning practitioners. Unlike prior work that benchmarks models and experimental setups, we take a human-computer interaction (HCI) perspective on how practitioners select source datasets. Our findings indicate that choices are task-dependent and influenced by community practices, dataset properties, and computational (data embedding), or perceived visual or semantic similarity. However, similarity ratings and expected performance are not always aligned, challenging a traditional "more similar is better" view. Moreover, ethical and fairness considerations remain largely absent from source dataset sections. Participants often used ambiguous terminology, which suggests a need for clearer definitions and tools to make them explicit and usable. By clarifying these heuristics and introducing a conceptual framework of transfer learning factors, this work provides practical insights for more systematic source selection in transfer learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_00902 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification Lu, Yucheng Zając, Hubert Dariusz Cheplygina, Veronika Jiménez-Sánchez, Amelia Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction Transfer learning is crucial for medical imaging, yet the selection of source datasets often relies on researchers' intuition rather than systematic principles, which can impact the generalizability of algorithms and, thus, patient outcomes. This study investigates these decisions through a task-based survey with machine learning practitioners. Unlike prior work that benchmarks models and experimental setups, we take a human-computer interaction (HCI) perspective on how practitioners select source datasets. Our findings indicate that choices are task-dependent and influenced by community practices, dataset properties, and computational (data embedding), or perceived visual or semantic similarity. However, similarity ratings and expected performance are not always aligned, challenging a traditional "more similar is better" view. Moreover, ethical and fairness considerations remain largely absent from source dataset sections. Participants often used ambiguous terminology, which suggests a need for clearer definitions and tools to make them explicit and usable. By clarifying these heuristics and introducing a conceptual framework of transfer learning factors, this work provides practical insights for more systematic source selection in transfer learning. |
| title | Intuitions of Machine Learning Researchers about Transfer Learning for Medical Image Classification |
| topic | Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2510.00902 |