DRTAM：双秩1张量注意力模块
DRTAM: Dual Rank-1 Tensor Attention Module
AI总结：
本文提出DRTAM（双秩1张量注意力模块），通过RTAM和RDEM生成初始与补充注意力图，在大型和移动网络上均实现自适应特征细化，性能优于现有注意力模块。
摘要：
最近，注意力机制在计算机视觉中被广泛研究，但很少有能在大型网络和移动网络上同时表现出色的。本文提出了双秩1张量注意力模块（DRTAM），一种用于前馈卷积神经网络的新型残差注意力学习引导的注意力模块。给定一个3D特征张量图，DRTAM首先沿三个轴生成三个2D特征描述符。然后，使用这三个描述符，DRTAM依次推断出两个秩1张量注意力图，即初始注意力图和补充注意力图，并将它们结合并乘以输入特征图以实现自适应特征细化（见图1(c)）。为生成这两个注意力图，DRTAM引入了秩1张量注意力模块（RTAM）和残差描述符提取模块（RDEM）：RTAM将每个2D特征描述符划分为多个块，并在每个块上采用条带池化，生成秩1张量注意力图的三个因子向量，从而能够分别沿三个维度捕获局部和长距离上下文信息；RDEM利用初始注意力图的三个因子向量和输入特征的三个描述符，生成残差特征的三个2D特征描述符，以产生补充注意力图。在ImageNet-1K、MS COCO和PASCAL VOC上的大量实验结果表明，与其他最先进的注意力模块相比，DRTAM在大型网络和移动网络上均取得了有竞争力的性能。
英文摘要：
Recently, attention mechanisms have been extensively investigated in computer vision, but few of them show excellent performance on both large and mobile networks. This paper proposes Dual Rank-1 Tensor Attention Module (DRTAM), a novel residual-attention-learning-guided attention module for feed-forward convolutional neural networks. Given a 3D feature tensor map, DRTAM firstly generates three 2D feature descriptors along three axes. Then, using three descriptors, DRTAM sequentially infers two rank-1 tensor attention maps, the initial attention map and the complement attention map, combines and multiplied them to the input feature map for adaptive feature refinement(see Fig.1(c)). To generate two attention maps, DRTAM introduces rank-1 tensor attention module (RTAM) and residual descriptors extraction module (RDEM): RTAM divides each 2D feature descriptors into several chunks, and generate three factor vectors of a rank-1 tensor attention map by employing strip pooling on each chunk so that local and long-range contextual information can be captured along three dimension respectively; RDEM generates three 2D feature descriptors of the residual feature to produce the complement attention map, using three factor vectors of the initial attention map and three descriptors of the input feature. Extensive experimental results on ImageNet-1K, MS COCO and PASCAL VOC demonstrate that DRTAM achieves competitive performance on both large and mobile networks compare with other state-of-the-art attention modules.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
