Kernel-Segregated Transpose Convolution Operation
This work addresses performance bottlenecks for deep learning practitioners using transpose convolutions, though it is incremental as it optimizes an existing operation without changing the fundamental paradigm.
The paper tackled the computational inefficiency of transpose convolution layers in deep learning by proposing an algorithmic optimization that segregates the kernel into four sub-kernels based on activations, resulting in up to 3.09x faster computation on a GPU and 2.2x faster training on a CPU.
Transpose convolution has shown prominence in many deep learning applications. However, transpose convolution layers are computationally intensive due to the increased feature map size due to adding zeros after each element in each row and column. Thus, convolution operation on the expanded input feature map leads to poor utilization of hardware resources. The main reason for unnecessary multiplication operations is zeros at predefined positions in the input feature map. We propose an algorithmic-level optimization technique for the effective transpose convolution implementation to solve these problems. Based on kernel activations, we segregated the original kernel into four sub-kernels. This scheme could reduce memory requirements and unnecessary multiplications. Our proposed method was $3.09 (3.02) \times$ faster computation using the Titan X GPU (Intel Dual Core CPU) with a flower dataset from the Kaggle website. Furthermore, the proposed optimization method can be generalized to existing devices without additional hardware requirements. A simple deep learning model containing one transpose convolution layer was used to evaluate the optimization method. It showed $2.2 \times$ faster training using the MNIST dataset with an Intel Dual-core CPU than the conventional implementation.