In SAS DLPy transfer learning, a ResNet-50 pre-trained on ImageNet is adapted for a 10-class medical image classification task. Which layers should initially be frozen during fine-tuning?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — c is correct because early convolutional layers in deep CNNs learn general, transferable features (edges, textures, shapes) useful across many image domains. Freezing them prevents losing these general representations while allowing later layers and the new classification head to adapt to the specific medical imaging domain.
Full explanation below image
Full Explanation
C is correct because early convolutional layers in deep CNNs learn general, transferable features (edges, textures, shapes) useful across many image domains. Freezing them prevents losing these general representations while allowing later layers and the new classification head to adapt to the specific medical imaging domain. A is wrong; freezing only the output layer while retraining all earlier layers defeats the purpose of transfer learning. B is wrong; freezing everything prevents any learning. D is wrong; full retraining discards the benefit of pre-trained features.