Search Results for author:
Found 2 papers, 1 papers with code
Proto2Proto: Can you recognize the car, the way I do?
With growing use cases of model reuse and distillation, there is a need to also study transfer of interpretability from one model to another.
Learning Transferable Feature Representations Using Neural Networks
Generally it requires labeled data from the source and only unlabeled data from the target to learn such representations.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
