Improving Shape Awareness and Interpretability in Deep Networks Using Geometric Moments

TL;DR

This paper introduces a deep learning model inspired by geometric moments to enhance shape awareness and interpretability in image classification, achieving better performance and understanding than standard models.

Contribution

A novel deep-learning approach using geometric moments to create shape-aware, interpretable features with improved classification accuracy.

Findings

Higher classification performance than baseline ResNet models

Significantly improved interpretability of features

Effective in standard image classification datasets

Abstract

Deep networks for image classification often rely more on texture information than object shape. While efforts have been made to make deep-models shape-aware, it is often difficult to make such models simple, interpretable, or rooted in known mathematical definitions of shape. This paper presents a deep-learning model inspired by geometric moments, a classically well understood approach to measure shape-related properties. The proposed method consists of a trainable network for generating coordinate bases and affine parameters for making the features geometrically invariant yet in a task-specific manner. The proposed model improves the final feature's interpretation. We demonstrate the effectiveness of our method on standard image classification datasets. The proposed model achieves higher classification performance compared to the baseline and standard ResNet models while substantially improving interpretability.