Towards Interpretable PolSAR Image Classification: Polarimetric Scattering Mechanism Informed Concept Bottleneck and Kolmogorov-Arnold Network

TL;DR

This paper introduces a novel interpretable deep learning framework for PolSAR image classification that leverages polarimetric scattering mechanisms and concept bottleneck networks to enhance transparency without sacrificing accuracy.

Contribution

It proposes a new structure called Parallel Concept Bottleneck Networks and integrates Kolmogorov-Arnold Networks for improved interpretability in PolSAR classification.

Findings

Achieves satisfactory classification accuracy with interpretable features.

Transforms high-dimensional features into human-understandable concepts.

Provides a functional mapping from concepts to categories using spline functions.

Abstract

In recent years, Deep Learning (DL) based methods have received extensive and sufficient attention in the field of PolSAR image classification, which show excellent performance. However, due to the ``black-box" nature of DL methods, the interpretation of the high-dimensional features extracted and the backtracking of the decision-making process based on the features are still unresolved problems. In this study, we first highlight this issue and attempt to achieve the interpretability analysis of DL-based PolSAR image classification technology with the help of Polarimetric Target Decomposition (PTD), a feature extraction method related to the scattering mechanism unique to the PolSAR image processing field. In our work, by constructing the polarimetric conceptual labels and a novel structure named Parallel Concept Bottleneck Networks (PaCBM), the uninterpretable high-dimensional features are transformed into human-comprehensible concepts based on physically verifiable polarimetric scattering mechanisms. Then, the Kolmogorov-Arnold Network (KAN) is used to replace Multi-Layer Perceptron (MLP) for achieving a more concise and understandable mapping process between layers and further enhanced non-linear modeling ability. The experimental results on several PolSAR datasets show that the features could be conceptualization under the premise of achieving satisfactory accuracy through the proposed pipeline, and the analytical function for predicting category labels from conceptual labels can be obtained by combining spline functions, thus promoting the research on the interpretability of the DL-based PolSAR image classification model.