Convolutional Feature Encoding Methods in DCNN

Question

In Computer Vision, feature encoding methods are used on pre-trained DCNN to increase the feature robustness to certain conditions such as viewpoint/appearance variations ref.

I was just wondering if there are already available well established methods among AI community with probably python implementations.

I found the following ones in literature but without any tutorial or code example:

1. Multi-layer pooling ref
2. Cross convolutional layer Pooling ref
3. Holistic Pooling ref