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

arXiv: https://arxiv.org/abs/2507.03315 · HTML: https://mlsanity.com/paper/2507.03315/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 67 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [KAN: Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2404.19756/) (2024)
- [Post-hoc Concept Bottleneck Models](https://mlsanity.com/paper/2205.15480/) (2022)
- [Label-Free Concept Bottleneck Models](https://mlsanity.com/paper/2304.06129/) (2023)
- [Editable Concept Bottleneck Models](https://mlsanity.com/paper/2405.15476/) (2024)
- [Physically Explainable CNN for SAR Image Classification](https://mlsanity.com/paper/2110.14144/) (2021)
- [Towards Concept-based Interpretability of Skin Lesion Diagnosis using Vision-Language Models](https://mlsanity.com/paper/2311.14339/) (2023)
- [PolSF: PolSAR image dataset on San Francisco](https://mlsanity.com/paper/1912.07259/) (2019)
- [Polarimetric Convolutional Network for PolSAR Image Classification](https://mlsanity.com/paper/1807.02975/) (2018)
- [Explainable Neural Network-based Modulation Classification via Concept Bottleneck Models](https://mlsanity.com/paper/2101.01239/) (2021)
- [Classification of Polarimetric SAR Images Using Compact Convolutional Neural Networks](https://mlsanity.com/paper/2011.05243/) (2020)

## Abstract (arXiv)

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.