Feature Relevance Evaluation using Grad-CAM, LIME and SHAP for Deep Learning SAR Data Classification
Authors:
- 12 September 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 457-462
Abstract
For predictive analysis and automatic classification, Deep Neural Networks (DNNs) are investigated and visualized. All the DNNs used for Automatic Target Recognition (ATR) have inbuilt feature extraction and classification abilities, but the inner working gets more opaque rendering them a black box as the networks get deeper and more complex. The main goal of this paper is to get a glimpse of what the network perceives in order to classify Moving and Stationary Target Acquisition and Recognition (MSTAR) targets. However, past works have shown that classification of targets was performed solely based on clutter within the MSTAR data. Here we show that the DNN trained on the MSTAR dataset classifies only based on target information and the clutter plays no role in it. To demonstrate this, heatmaps are generated using the Gradient-weighted Class Activation Mapping (Grad-CAM) method to highlight the areas of attention in each input Synthetic Aperture Radar (SAR) image. To further probe into the interpretability of classifiers, reliable post hoc explanation techniques are used such as Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) to approximate the behaviour of a black box by extracting relationships between feature value and prediction.Keywords
This publication has 10 references indexed in Scilit:
- On the Tractability of SHAP ExplanationsProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysisAccident Analysis & Prevention, 2020
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based LocalizationInternational Journal of Computer Vision, 2019
- SAR ATR of Ground Vehicles Based on ESENetRemote Sensing, 2019
- Automatic Target Recognition Strategy for Synthetic Aperture Radar Images Based on Combined Discrimination TreesComputational Intelligence and Neuroscience, 2017
- A deep learning SAR ATR system using regularization and prioritized classes2017
- SAR ATR by a combination of convolutional neural network and support vector machinesIEEE Transactions on Aerospace and Electronic Systems, 2016
- "Why Should I Trust You?"2016
- Non-cooperative target identification of battlefield targets - classification results based on SAR images2005
- Analysis of regression in game theory approachApplied Stochastic Models in Business and Industry, 2001