To enhance the capability of neural networks, research on attention mechanism have been deepened. In this area, attention modules make forward inference along channel dimension and spatial dimension sequentially, parallelly, or simultaneously. However, we have found that spatial attention modules mainly apply convolution layers to generate attention maps, which aggregate feature responses only based on local receptive fields. In this article, we take advantage of this finding to create a nonlocal spatial attention module (NL-SAM), which collects context information from all pixels to adaptively recalibrate spatial responses in a convolutional feature map. NL-SAM overcomes the limitations of repeating local operations and exports a 2D spatial attention map to emphasize or suppress responses in different locations. Experiments on three benchmark datasets show at least 0.58% improvements on variant ResNets. Furthermore, this module is simple and can be easily integrated with existing channel attention modules, such as squeeze-and-excitation and gather-excite, to exceed these significant models at a minimal additional computational cost (0.196%).

中文翻译：

---

用于图像分类的非局部空间注意模块

为了增强神经网络的能力，注意力机制的研究得到了深化。在这个领域，注意力模块沿着通道维度和空间维度顺序、并行或同时进行前向推理。然而，我们发现空间注意力模块主要应用卷积层来生成注意力图，它仅基于局部感受野聚合特征响应。在本文中，我们利用这一发现创建了一个非局部空间注意模块 (NL-SAM)，该模块从所有像素收集上下文信息，以自适应地重新校准卷积特征图中的空间响应。NL-SAM 克服了重复局部操作的局限性，并导出 2D 空间注意力图以强调或抑制不同位置的响应。在三个基准数据集上的实验表明，在变体 ResNet 上至少有 0.58% 的改进。此外，这个模块很简单，可以很容易地与现有的通道注意力模块集成，例如挤压和激发和聚集激发，以最小的额外计算成本 (0.196%) 超越这些重要的模型。