arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.08382cs.CVcs.LG
收藏

DMSANet:双多尺度注意力网络

DMSANet: Dual Multi Scale Attention Network

Vellore Institute of Technology(韦洛尔理工大学)

Abhinav Sagar

摘要:

最近注意力机制在计算机视觉界非常流行。人们已经做了大量的工作来提高网络的性能,尽管这几乎总是导致计算复杂性的增加。在本文中,我们提出了一个新的注意力模块,不仅实现了最佳的性能,但也有较少的参数相比,大多数现有的模型。我们的注意力模块可以很容易地与其他卷积神经网络集成,因为它是轻量级的。提出的网络命名为双多尺度注意力网络(DMSANet)是由两部分组成:第一部分是用来在不同的尺度上提取特征和聚合它们,第二部分使用空间和通道注意力模块并行自适应地集成本地功能与它们的全局依赖关系。我们对ImageNet数据集上的图像分类、MS COCO数据集上的目标检测和实例分割的网络性能进行了基准测试。

英文摘要:

Attention mechanism of late has been quite popular in the computer vision community. A lot of work has been done to improve the performance of the network, although almost always it results in increased computational complexity. In this paper, we propose a new attention module that not only achieves the best performance but also has lesser parameters compared to most existing models. Our attention module can easily be integrated with other convolutional neural networks because of its lightweight nature. The proposed network named Dual Multi Scale Attention Network (DMSANet) is comprised of two parts: the first part is used to extract features at various scales and aggregate them, the second part uses spatial and channel attention modules in parallel to adaptively integrate local features with their global dependencies. We benchmark our network performance for Image Classification on ImageNet dataset, Object Detection and Instance Segmentation both on MS COCO dataset.

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。

↑