CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks

arXiv:2405.05755v1 Announce Type: cross
Abstract: In recent years, convolutional neural networks (CNNs) with channel-wise feature refining mechanisms have brought noticeable benefits to modelling channel dependencies. However, current attention paradigms fail to infer an optimal channel descriptor capable of simultaneously exploiting statistical and spatial relationships among feature maps. In this paper, to overcome this shortcoming, we present a novel channel-wise spatially autocorrelated (CSA) attention mechanism. Inspired by geographical analysis, the proposed CSA exploits the spatial relationships between channels of feature maps …

abstract arxiv attention benefits cnns convolutional convolutional neural networks cs.ai cs.cv cs.lg current dependencies feature however maps modelling networks neural networks paper relationships spatial statistical type wise