2 Hits in 2.1 sec

CheXtransfer: Performance and Parameter Efficiency of ImageNet Models for Chest X-Ray Interpretation [article]

Alexander Ke, William Ellsworth, Oishi Banerjee, Andrew Y. Ng, Pranav Rajpurkar
2021 arXiv   pre-print
Deep learning methods for chest X-ray interpretation typically rely on pretrained models developed for ImageNet.  ...  Our work contributes new experimental evidence about the relation of ImageNet to chest x-ray interpretation performance.  ...  In closing, our work contributes to the understanding of the transfer performance and parameter efficiency of ImageNet models for chest X-ray interpretation.  ... 
arXiv:2101.06871v1 fatcat:o62igm4us5c6ff2ychwshxrk24

HistoTransfer: Understanding Transfer Learning for Histopathology [article]

Yash Sharma, Lubaina Ehsan, Sana Syed, Donald E. Brown
2021 arXiv   pre-print
In this work, we compare the performance of features extracted from networks trained on ImageNet and histopathology data.  ...  Further, to examine if intermediate block representation is better suited for feature extraction and ImageNet architectures are unnecessarily large for histopathology, we truncate the blocks of ResNet18  ...  extraction step resulting in a parameter-efficient model and higher-resolution class activation map visualizations (CAM) for interpretability.  ... 
arXiv:2106.07068v1 fatcat:mw3c4adekjbddbuhuv6g2jpaiu