Visualizing Classification Structure of Large-Scale Classifiers
Computer Vision and Pattern Recognition
2020-07-21 v2 Machine Learning
Machine Learning
Abstract
We propose a measure to compute class similarity in large-scale classification based on prediction scores. Such measure has not been formally pro-posed in the literature. We show how visualizing the class similarity matrix can reveal hierarchical structures and relationships that govern the classes. Through examples with various classifiers, we demonstrate how such structures can help in analyzing the classification behavior and in inferring potential corner cases. The source code for one example is available as a notebook at https://github.com/bilalsal/blocks
Keywords
Cite
@article{arxiv.2007.06068,
title = {Visualizing Classification Structure of Large-Scale Classifiers},
author = {Bilal Alsallakh and Zhixin Yan and Shabnam Ghaffarzadegan and Zeng Dai and Liu Ren},
journal= {arXiv preprint arXiv:2007.06068},
year = {2020}
}
Comments
2020 ICML Workshop on Human Interpretability in Machine Learning (WHI 2020)