Radius Adaptive Convolutional Neural Network
This addresses efficiency issues for computer vision applications, though it appears incremental as a modification to standard convolution.
The paper tackles the high computational cost of convolutional neural networks (CNNs) in image processing by proposing a radius-adaptive convolution that adjusts kernel sizes based on input content, resulting in higher speeds while maintaining a similar number of weights.
Convolutional neural network (CNN) is widely used in computer vision applications. In the networks that deal with images, CNNs are the most time-consuming layer of the networks. Usually, the solution to address the computation cost is to decrease the number of trainable parameters. This solution usually comes with the cost of dropping the accuracy. Another problem with this technique is that usually the cost of memory access is not taken into account which results in insignificant speedup gain. The number of operations and memory access in a standard convolution layer is independent of the input content, which makes it limited for certain accelerations. We propose a simple modification to a standard convolution to bridge this gap. We propose an adaptive convolution that adopts different kernel sizes (or radii) based on the content. The network can learn and select the proper radius based on the input content in a soft decision manner. Our proposed radius-adaptive convolutional neural network (RACNN) has a similar number of weights to a standard one, yet, results show it can reach higher speeds. The code has been made available at: https://github.com/meisamrf/racnn.