Efficient forward propagation of time-sequences in convolutional neural networks using Deep Shifting
This addresses efficiency issues for real-time applications using CNNs on time-sequences, but it is incremental as it builds on existing CNN methods.
The paper tackled the problem of redundant convolution operations in CNNs for continuously updating time-sequences by proposing Deep Shifting, which remembers previous results to minimize calculations, achieving at least a constant and up to quadratic reduction in complexity and significant computation time savings, especially with many time-frames.
When a Convolutional Neural Network is used for on-the-fly evaluation of continuously updating time-sequences, many redundant convolution operations are performed. We propose the method of Deep Shifting, which remembers previously calculated results of convolution operations in order to minimize the number of calculations. The reduction in complexity is at least a constant and in the best case quadratic. We demonstrate that this method does indeed save significant computation time in a practical implementation, especially when the networks receives a large number of time-frames.