DeepLofargram: A Deep Learning based Fluctuating Dim Frequency Line Detection and Recovery

Abstract

This paper investigates the problem of dim frequency line detection and recovery in the so-called lofargram. Theoretically, time integration long enough can always enhance the detection characteristic. But this does not hold for irregularly fluctuating lines. Deep learning has been shown to perform very well for sophisticated visual inference tasks. With the composition of multiple processing layers, very complex high level representation that amplify the important aspects of input while suppresses irrelevant variations can be learned. Hence we propose a new DeepLofargram, composed of deep convolutional neural network and its visualization counterpart. Plugging into specifically designed multi-task loss, an end-to-end training jointly learns to detect and recover the spatial location of potential lines. Leveraging on this deep architecture, the performance boundary is -24dB on average, and -26dB for some. This is far beyond the perception of human visual and significantly improves the state-of-the-art.

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Striving for Simplicity: The All Convolutional Net
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Machine learning in acoustics: theory and applications
• Sparse Bayesian learning with uncertainty models and multiple dictionaries