Improving Explainability of Softmax Classifiers Using a Prototype-Based Joint Embedding Method

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sit, Hilarie, Keith, Brendan, Bergen, Karianne
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909256431697920
author Sit, Hilarie
Keith, Brendan
Bergen, Karianne
author_facet Sit, Hilarie
Keith, Brendan
Bergen, Karianne
contents We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates potential for out of distribution detection (OOD). By modifying the model architecture and training to make predictions using similarities to any set of class examples from the training dataset, we acquire the ability to sample for prototypical examples that contributed to the prediction, which provide an instance-based explanation for the model's decision. Furthermore, by learning relationships between images from the training dataset through relative distances within the model's latent space, we obtain a metric for uncertainty that is better able to detect out of distribution data than softmax confidence.
format Preprint
id arxiv_https___arxiv_org_abs_2407_02271
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Improving Explainability of Softmax Classifiers Using a Prototype-Based Joint Embedding Method
Sit, Hilarie
Keith, Brendan
Bergen, Karianne
Machine Learning
We propose a prototype-based approach for improving explainability of softmax classifiers that provides an understandable prediction confidence, generated through stochastic sampling of prototypes, and demonstrates potential for out of distribution detection (OOD). By modifying the model architecture and training to make predictions using similarities to any set of class examples from the training dataset, we acquire the ability to sample for prototypical examples that contributed to the prediction, which provide an instance-based explanation for the model's decision. Furthermore, by learning relationships between images from the training dataset through relative distances within the model's latent space, we obtain a metric for uncertainty that is better able to detect out of distribution data than softmax confidence.
title Improving Explainability of Softmax Classifiers Using a Prototype-Based Joint Embedding Method
topic Machine Learning
url https://arxiv.org/abs/2407.02271