Don't Think It Twice: Exploit Shift Invariance for Efficient Online
Streaming Inference of CNNs
Don't Think It Twice: Exploit Shift Invariance for Efficient Online
Streaming Inference of CNNs
Deep learning time-series processing often relies on convolutional neural networks with overlapping windows. This overlap allows the network to produce an output faster than the window length. However, it introduces additional computations. This work explores the potential to optimize computational efficiency during inference by exploiting convolution's shift-invariance properties to skip …