Reflective-Net: Learning from Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schneider, Johannes, Vlachos, Michalis
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915180558942208
author Schneider, Johannes
Vlachos, Michalis
author_facet Schneider, Johannes
Vlachos, Michalis
contents We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as well as to reflect on their own thinking and learn from explanations. To the best of our knowledge, this is the first time that the potential of mimicking this process by using explanations generated by explainability methods has been explored. We found that combining explanations with traditional labeled data leads to significant improvements in classification accuracy and training efficiency across multiple image classification datasets and convolutional neural network architectures. It is worth noting that during training, we not only used explanations for the correct or predicted class, but also for other classes. This serves multiple purposes, including allowing for reflection on potential outcomes and enriching the data through augmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2011_13986
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Reflective-Net: Learning from Explanations
Schneider, Johannes
Vlachos, Michalis
Machine Learning
Artificial Intelligence
We examine whether data generated by explanation techniques, which promote a process of self-reflection, can improve classifier performance. Our work is based on the idea that humans have the ability to make quick, intuitive decisions as well as to reflect on their own thinking and learn from explanations. To the best of our knowledge, this is the first time that the potential of mimicking this process by using explanations generated by explainability methods has been explored. We found that combining explanations with traditional labeled data leads to significant improvements in classification accuracy and training efficiency across multiple image classification datasets and convolutional neural network architectures. It is worth noting that during training, we not only used explanations for the correct or predicted class, but also for other classes. This serves multiple purposes, including allowing for reflection on potential outcomes and enriching the data through augmentation.
title Reflective-Net: Learning from Explanations
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2011.13986