A METHOD FOR TRAINING SHALLOW CONVOLUTIONAL NEURAL NETWORKS FOR INFRARED TARGET DETECTION USING A TWO-PHASE LEARNING STRATEGY

摘要

The present invention discloses a method for training shallow convolutional neural networks for infrared target detection using a two-phase learning strategy, that can converge to satisfactory detection performance, even with scale-invariance capability. In first step, the aim is to ensure that only filters in the convolutional layer produce semantic features that serve the problem of target detection. L2-norm (Euclidian norm) was used as loss function for the stable training of semantic filters obtained from the convolutional layers. Later, only the decision layers are trained by transferring the weight values in the convolutional layers completely and freezing the learning rate. In this step, unlike the first, the L1-norm (mean-absolute-deviation) loss function is used.