The attention mechanism is widely used in the field of semantic segmentation, due to the fact that it can be used to obtain effective long-distance dependencies by assigning different weights to objects according to different tasks. We propose a novel Nested Attention Network (NANet) for semantic segmentation, which combines Feature Category Attention (FCA) and Channel Relationship Attention (CRA) to effectively aggregate same-category contexts in both spatial and channel dimensions. Specifically, FCA captures the dependencies between spatial pixel features and categories to achieve the aggregation of features of the same category. CRA further captures the channel relationships on the output of FCA to obtain richer contexts. Numerous experiments have shown that NANet has a lower number of parameters and computational complexity than other state-of-the-art methods, and is a lightweight model with a lower total number of floating-point operations. We evaluated the performance of NANet on three datasets: Cityscapes, PASCAL VOC 2012, and ADE20K, and the experimental results show that NANet obtains promising results, reaching a performance of 82.6% on the Cityscapes test set.

注意力机制广泛应用于语义分割领域，因为它可以根据不同的任务为对象分配不同的权重来获得有效的长距离依赖关系。我们提出了一种用于语义分割的新颖的嵌套注意力网络（NANet），它结合了特征类别注意力（FCA）和通道关系注意力（CRA）来有效聚合空间和通道维度上的同类别上下文。具体来说，FCA捕获空间像素特征与类别之间的依赖关系，以实现同一类别特征的聚合。 CRA 进一步捕获 FCA 输出上的渠道关系以获得更丰富的上下文。大量实验表明，NANet 比其他最先进的方法具有更低的参数数量和计算复杂度，并且是浮点运算总数较低的轻量级模型。我们在三个数据集上评估了 NANet 的性能：Cityscapes、PASCAL VOC 2012 和 ADE20K，实验结果表明 NANet 获得了可喜的结果，在 Cityscapes 测试集上达到了 82.6% 的性能。