LIME-Based Data Selection Method for SAR Images Generation Using GAN
Open Access
- 3 January 2022
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 14 (1) , 204
Abstract
Deep learning has obtained remarkable achievements in computer vision, especially image and video processing. However, in synthetic aperture radar (SAR) image recognition, the application of DNNs is usually restricted due to data insufficiency. To augment datasets, generative adversarial networks (GANs) are usually used to generate numerous photo-realistic SAR images. Although there are many pixel-level metrics to measure GAN’s performance from the quality of generated SAR images, there are few measurements to evaluate whether the generated SAR images include the most representative features of the target. In this case, the classifier probably categorizes a SAR image into the corresponding class based on “wrong” criterion, i.e., “Clever Hans”. In this paper, local interpretable model-agnostic explanation (LIME) is innovatively utilized to evaluate whether a generated SAR image possessed the most representative features of a specific kind of target. Firstly, LIME is used to visualize positive contributions of the input SAR image to the correct prediction of the classifier. Subsequently, these representative SAR images can be selected handily by evaluating how much the positive contribution region matches the target. Experimental results demonstrate that the proposed method can ally “Clever Hans” phenomenon greatly caused by the spurious relationship between generated SAR images and the corresponding classes.Keywords
Funding Information
- science and technology project of Xianyang City (2021ZDZX-GY-0001)
- Fundamental Research Funds for the Central Universities (JB210206, JC2111)
This publication has 19 references indexed in Scilit:
- A MIMO-SAR Tomography Algorithm Based on Fully-Polarimetric DataSensors, 2019
- Unmasking Clever Hans predictors and assessing what machines really learnNature Communications, 2019
- How Good Is My GAN?2018
- Interpretable Explanations of Black Boxes by Meaningful Perturbation2017
- Explaining nonlinear classification decisions with deep Taylor decompositionPattern Recognition, 2017
- Data Augmentation by Multilevel Reconstruction Using Attributed Scattering Center for SAR Target RecognitionIEEE Geoscience and Remote Sensing Letters, 2017
- "Why Should I Trust You?"2016
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- TurboPixels: Fast Superpixels Using Geometric FlowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Efficient Simulation of hybrid stripmap/spotlight SAR raw signals from extended scenesIEEE Transactions on Geoscience and Remote Sensing, 2004