CPWC: Contextual Point Wise Convolution for Object Recognition
This addresses a bottleneck in convolutional neural networks for object recognition, offering an incremental improvement over standard PWC methods.
The paper tackles the limitation of pointwise convolution (PWC) in ignoring spatial information, proposing a contextual PWC design that uses spatial input efficiently, resulting in significant performance improvements for classification and detection without substantially increasing parameters or computations.
Convolutional layers are a major driving force behind the successes of deep learning. Pointwise convolution (PWC) is a 1x1 convolutional filter that is primarily used for parameter reduction. However, the PWC ignores the spatial information around the points it is processing. This design is by choice, in order to reduce the overall parameters and computations. However, we hypothesize that this shortcoming of PWC has a significant impact on the network performance. We propose an alternative design for pointwise convolution, which uses spatial information from the input efficiently. Our design significantly improves the performance of the networks without substantially increasing the number of parameters and computations. We experimentally show that our design results in significant improvement in the performance of the network for classification as well as detection.