CNN Transfer Learning with CNNs 3

Question 1

Which popular pretrained CNN architecture introduced depthwise separable convolutions, making it efficient for transfer learning on mobile devices?

Accepted Answer

MobileNet

Answer

MobileNet uses depthwise separable convolutions to dramatically reduce computation, making it ideal for mobile and embedded transfer learning.

Question 2

When the target dataset is large and very different from the source dataset, the recommended transfer learning approach is:

Accepted Answer

Fine-tune the entire network or train from scratch

Answer

With a large, dissimilar target dataset, full fine-tuning or training from scratch allows the model to learn domain-specific features.

Question 3

What is the purpose of using a lower learning rate for earlier (pretrained) layers compared to later layers during fine-tuning?

Accepted Answer

To preserve general low-level features while adapting high-level ones

Answer

Lower learning rates in early layers preserve generalizable edge/texture detectors, while higher rates in later layers adapt task-specific representations.

Question 4

In transfer learning, 'bottleneck features' refer to:

Accepted Answer

Compressed features stored in bottleneck files for fast retrieval

Answer

Bottleneck features are precomputed activations from the pretrained base saved to disk, enabling fast classifier training without re-running the backbone.

Question 5

ResNet's skip connections primarily help transfer learning by:

Accepted Answer

Preventing vanishing gradients and enabling very deep pretrained models

Answer

Skip connections allow gradients to flow directly through the network, enabling training of very deep ResNets that provide rich pretrained features.

CNN - Convolutional Neural Networks Practice Test

CNN - Convolutional Neural Networks Practice Test

CNN Transfer Learning with CNNs 3