This Looks Better than That: Better Interpretable Models with ProtoPNeXt
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913399476060160 |
|---|---|
| author | Willard, Frank Moffett, Luke Mokel, Emmanuel Donnelly, Jon Guo, Stark Yang, Julia Kim, Giyoung Barnett, Alina Jade Rudin, Cynthia |
| author_facet | Willard, Frank Moffett, Luke Mokel, Emmanuel Donnelly, Jon Guo, Stark Yang, Julia Kim, Giyoung Barnett, Alina Jade Rudin, Cynthia |
| contents | 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 an angular prototype similarity metric to the original ProtoPNet is sufficient to produce new state-of-the-art accuracy for prototypical-part models on CUB-200 across multiple backbones. We further deploy this framework to jointly optimize for accuracy and prototype interpretability as measured by metrics included in ProtoPNeXt. Using the same resources, this produces models with substantially superior semantics and changes in accuracy between +1.3% and -1.5%. The code and trained models will be made publicly available upon publication. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14675 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | This Looks Better than That: Better Interpretable Models with ProtoPNeXt Willard, Frank Moffett, Luke Mokel, Emmanuel Donnelly, Jon Guo, Stark Yang, Julia Kim, Giyoung Barnett, Alina Jade Rudin, Cynthia Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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 an angular prototype similarity metric to the original ProtoPNet is sufficient to produce new state-of-the-art accuracy for prototypical-part models on CUB-200 across multiple backbones. We further deploy this framework to jointly optimize for accuracy and prototype interpretability as measured by metrics included in ProtoPNeXt. Using the same resources, this produces models with substantially superior semantics and changes in accuracy between +1.3% and -1.5%. The code and trained models will be made publicly available upon publication. |
| title | This Looks Better than That: Better Interpretable Models with ProtoPNeXt |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2406.14675 |