Spatial attention has been widely used to improve the performance of convolutional neural networks by allowing them to focus on important information. However, it has certain limitations. In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that it can solve the problem of convolutional kernel parameter sharing. Despite this, the information contained in the attention map generated by spatial attention is not sufficient for large-size convolutional kernels. Therefore, we introduce a new attention mechanism called Receptive-Field Attention (RFA). While previous attention mechanisms such as the Convolutional Block Attention Module (CBAM) and Coordinate Attention (CA) only focus on spatial features, they cannot fully address the issue of convolutional kernel parameter sharing. In contrast, RFA not only focuses on the receptive-field spatial feature but also provides effective attention weights for large-size convolutional kernels. The Receptive-Field Attention convolutional operation (RFAConv), developed by RFA, represents a new approach to replace the standard convolution operation. It offers nearly negligible increment of computational cost and parameters, while significantly improving network performance. We conducted a series of experiments on ImageNet-1k, MS COCO, and VOC datasets, which demonstrated the superiority of our approach in various tasks including classification, object detection, and semantic segmentation. Of particular importance, we believe that it is time to shift focus from spatial features to receptive-field spatial features for current spatial attention mechanisms. By doing so, we can further improve network performance and achieve even better results. The code and pre-trained models for the relevant tasks can be found at https://github.com/Liuchen1997/RFAConv.

翻译：空间注意力已广泛应用于提升卷积神经网络性能，使其能够聚焦于重要信息。然而，空间注意力存在一定的局限性。本文提出了一种关于空间注意力有效性的新视角，即它能够解决卷积核参数共享的问题。尽管如此，由空间注意力生成的注意力图所包含的信息对于大尺寸卷积核而言仍不充分。为此，我们引入了一种名为感受野注意力（Receptive-Field Attention, RFA）的新注意力机制。以往的注意力机制，如卷积块注意力模块（CBAM）和坐标注意力（Coordinate Attention, CA），仅关注空间特征，无法完全解决卷积核参数共享的问题。相比之下，RFA不仅关注感受野空间特征，还能为大尺寸卷积核提供有效的注意力权重。基于RFA开发的感受野注意力卷积操作（RFAConv）代表了替代标准卷积操作的新方法。它在带来几乎可忽略不计的计算成本和参数增加的同时，显著提升了网络性能。我们在ImageNet-1k、MS COCO和VOC数据集上开展了一系列实验，验证了本方法在图像分类、目标检测和语义分割等多种任务中的优越性。尤为重要的是，我们认为当前的空间注意力机制应将关注点从空间特征转向感受野空间特征。通过这一转变，我们能够进一步提升网络性能并取得更优结果。相关任务的代码与预训练模型可在https://github.com/Liuchen1997/RFAConv获取。