Graph-based Active Learning for Semi-supervised Classification of SAR Data

TL;DR

This paper introduces a graph-based active learning approach using CNNVAE embeddings for semi-supervised SAR data classification, effectively reducing the need for labeled data and enabling human-in-the-loop labeling.

Contribution

The novel integration of CNNVAE embeddings with graph-based semi-supervised learning and active learning for SAR data classification.

Findings

Effective with small labeled datasets

Improves generalization over traditional methods

Enables human-in-the-loop active learning

Abstract

We present a novel method for classification of Synthetic Aperture Radar (SAR) data by combining ideas from graph-based learning and neural network methods within an active learning framework. Graph-based methods in machine learning are based on a similarity graph constructed from the data. When the data consists of raw images composed of scenes, extraneous information can make the classification task more difficult. In recent years, neural network methods have been shown to provide a promising framework for extracting patterns from SAR images. These methods, however, require ample training data to avoid overfitting. At the same time, such training data are often unavailable for applications of interest, such as automatic target recognition (ATR) and SAR data. We use a Convolutional Neural Network Variational Autoencoder (CNNVAE) to embed SAR data into a feature space, and then construct a similarity graph from the embedded data and apply graph-based semi-supervised learning techniques. The CNNVAE feature embedding and graph construction requires no labeled data, which reduces overfitting and improves the generalization performance of graph learning at low label rates. Furthermore, the method easily incorporates a human-in-the-loop for active learning in the data-labeling process. We present promising results and compare them to other standard machine learning methods on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset for ATR with small amounts of labeled data.