Transfer Learning on Autoencoders? I want to use the encoder of my autoencoder for feature extraction in an image anomaly detection framework.
For that reason, I thought that pretraining the autoencoder on a large dataset and then fine-tuning it on my target dataset would be a good idea. This idea crossed my mind because many anomaly detection approaches use CNN architectures like VGG, ResNet etc. as a feature extractor, which are pretrained on ImageNet.
I did not find papers regarding this matter and therefore my question if transfer learning is even really used on autoencoders?
 A: This approach often used in NLP models, so called via tuning and it is what you called transfer learning. A recent debate on this so called Foundation models actually revolves around this concept.

transfer learning is even really used on autoencoders?

Yes, it is possible, as these new foundation models approach training a large vision models or autoencoders. However, VGG or Resnet are very tiny models to be used as a foundational model compare to language models like GPT-3 or similar in size and training data coverage.
A: That is certainly possible to do, but somewhat different that the other image recognition approaches you mentioned.  With those approaches, the encoding that you use in transfer learning has been optimized for some image recognition task, so the it likely has features that are beneficial for that task.  Fine tuning just takes a previously optimized set of features and adjusts them slightly to the new task.
An autoencoder is trained to create an embedding that can reproduce the original data space - an unsupervised machine learning problem - but there is no reason that embedding is useful for another task.  It might be, but it wasn't trained for that purpose, so it might not have the right structure for a supervised machine learning problem.
