HIGHLIGHTS
- who: IJ-AI from the School of Digital Science, Universiti have published the paper: IAES International Journal of Artificial Intelligence (IJ-AI), in the Journal: (JOURNAL) of Jul/19,/2021
- what: The authors compare the performance of 14 pre-trained ImageNet models on the histopathologic dataset where each model has been configured as naive model feature extractor model or fine-tuned model. This research has shown that Densenet161 outperforms other architectures, with an AUC score of 0.9924 and F1 Sore 0.95 in the feature extractor model.
- future: The usefulness of transfer . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.