This Looks Better than That: Better Interpretable Models with ProtoPNeXt

arXiv:2406.14675v1 Announce Type: cross
Abstract: Prototypical-part models are a popular interpretable alternative to black-box deep learning models for computer vision. However, they are difficult to train, with high sensitivity to hyperparameter tuning, inhibiting their application to new datasets and our understanding of which methods truly improve their performance. To facilitate the careful study of prototypical-part networks (ProtoPNets), we create a new framework for integrating components of prototypical-part models -- ProtoPNeXt. Using ProtoPNeXt, we show that applying Bayesian hyperparameter tuning and …

abstract alternative application arxiv box computer computer vision cs.ai cs.cv cs.lg datasets deep learning however hyperparameter part performance popular sensitivity train tuning type understanding vision