← Search

Johan Fredin Haslum

2 accepted papers

2022

What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors

CVPR 2022poster

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 image characteristics between the domains. However, it is unclear what factor…

Cited by 118PDFcodeScholar
2020

Adding seemingly uninformative labels helps in low data regimes

ICML 2020poster

Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which encourages learning of enriched features. This raises the question of whether this remains true when data is scarce - is there an advantage t…