CFARnet: deep learning for target detection with constant false alarm rate

We consider the problem of target detection with a constant false alarm rate (CFAR). This constraint is crucial in many practical applications and is a standard requirement in classical composite hypothesis testing. In settings where classical approaches are computationally expensive or where only data samples are given, Bayesian and machine learning methodologies are advantageous. CFAR is less understood in these settings. To close this gap, we introduce a framework of CFAR constrained detectors. Theoretically, we prove that a CFAR constrained Bayes optimal detector is asymptotically equivalent to the classical generalized likelihood ratio test (GLRT). Practically, we develop a deep learning framework for fitting neural networks that approximate it. Experiments in both model based target detection and data-driven hyper-spectral images demonstrates that the proposed CFARnet allows a flexible tradeoff between CFAR and accuracy. In many problems near CFAR detectors can be developed with a small loss in accuracy.