6 citations · 15 across the 11 of their papers we have counts for
4 papers · 1 filter
Rashomon Sets for Prototypical-Part Networks: Editing Interpretable Models in Real-Time
Jon Donnelly, Zhicheng Guo, Alina Jade Barnett +3
Interpretability is critical for machine learning models in high-stakes settings because it allows users to verify the model's reasoning. In computer vision, prototypical part mode…
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
Chiyu Ma, Jon Donnelly, Wenjun Liu +3
We present ProtoViT, a method for interpretable image classification combining deep learning and case-based reasoning. This method classifies an image by comparing it to a set of l…
This Looks Better than That: Better Interpretable Models with ProtoPNeXt
Frank Willard, Luke Moffett, Emmanuel Mokel +6
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…
FPN-IAIA-BL: A Multi-Scale Interpretable Deep Learning Model for Classification of Mass Margins in Digital Mammography
Julia Yang, Alina Jade Barnett, Jon Donnelly +6
Digital mammography is essential to breast cancer detection, and deep learning offers promising tools for faster and more accurate mammogram analysis. In radiology and other high-s…