Explainable Metric Learning for Deflating Data Bias

TL;DR

This paper introduces an explainable metric learning framework that constructs hierarchical semantic segments for images, enhancing interpretability and reducing data bias, while significantly improving classification accuracy.

Contribution

It proposes a novel hierarchical, explainable metric learning approach that improves interpretability and bias reduction in image classification tasks.

Findings

Improves model accuracy over state-of-the-art methods

Enables human-understandable similarity measurement

Reduces bias in training datasets

Abstract

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep learning models, these approaches lack explainability, where the classification results are hard to interpret in a human-understandable way. In this paper, we present an explainable metric learning framework, which constructs hierarchical levels of semantic segments of an image for better interpretability. The key methodology involves a bottom-up learning strategy, starting by training the local metric learning model for the individual segments and then combining segments to compose comprehensive metrics in a tree. Specifically, our approach enables a more human-understandable similarity measurement between two images based on the semantic segments within it, which can be utilized to generate new samples to reduce bias in a training dataset. Extensive experimental evaluation demonstrates that the proposed approach can drastically improve model accuracy compared with state-of-the-art methods.