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 to produce an effective channel descriptor. To the best of our knowledge, this is the f irst time that the concept of geographical spatial analysis is utilized in deep CNNs. The proposed CSA imposes negligible learning parameters and light computational overhead to the deep model, making it a powerful yet efficient attention module of choice. We validate the effectiveness of the proposed CSA networks (CSA-Nets) through extensive experiments and analysis on ImageNet, and MS COCO benchmark datasets for image classification, object detection, and instance segmentation. The experimental results demonstrate that CSA-Nets are able to consistently achieve competitive performance and superior generalization than several state-of-the-art attention-based CNNs over different benchmark tasks and datasets.

翻译：近年来，具有通道级特征细化机制的卷积神经网络（CNN）在建模通道依赖性方面取得了显著成效。然而，当前的注意力范式无法推断出能够同时利用特征图统计关系和空间关系的最优通道描述符。本文为克服这一缺陷，提出了一种新颖的通道级空间自相关（CSA）注意力机制。受地理分析启发，所提出的CSA通过挖掘特征图通道间的空间关系来生成有效的通道描述符。据我们所知，这是地理空间分析概念首次被应用于深度CNN中。该机制为深度模型引入的可学习参数和计算开销极小，使其成为兼具强大性能与高效性的注意力模块选择。我们通过在ImageNet和MS COCO基准数据集上对图像分类、目标检测及实例分割任务进行大量实验与分析，验证了所提出的CSA网络（CSA-Nets）的有效性。实验结果表明，CSA-Nets能够在不同基准任务和数据集上持续取得具有竞争力的性能，并展现出比当前多种最先进的基于注意力的CNN更优越的泛化能力。