Name
Abstract | ||
|---|---|---|
Knowledge transfer impacts the performance of deep learning - the state of the art for image classification tasks, including automated melanoma screening. Deep learning's greed for large amounts of training data poses a challenge for medical tasks, which we can alleviate by recycling knowledge from models trained on different tasks, in a scheme called transfer learning. Although much of the best art on automated melanoma screening employs some form of transfer learning, a systematic evaluation was missing. Here we investigate the presence of transfer, from which task the transfer is sourced, and the application of fine tuning (i.e., retraining of the deep learning model after transfer). We also test the impact of picking deeper (and more expensive) models. Our results favor deeper models, pretrained over ImageNet, with fine-tuning, reaching an AUC of 80.7% and 84.5% for the two skin-lesion datasets evaluated. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ISBI.2017.7950523 | 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017) |
Keywords | DocType | Volume |
Melanoma screening,dermoscopy,deep learning,transfer learning | Conference | abs/1703.07479 |
ISBN | Citations | PageRank |
978-1-5090-1173-5 | 14 | 0.76 |
References | Authors | |
15 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Afonso Menegola | 1 | 30 | 2.54 |
| Michel Fornaciali | 2 | 39 | 3.94 |
| Ramon Pires | 3 | 34 | 3.26 |
| Flávia Vasques Bittencourt | 4 | 25 | 2.32 |
| Sandra Eliza Fontes de Avila | 5 | 377 | 15.15 |
| Eduardo Valle | 6 | 373 | 22.17 |