VIP内容

本文提出一种概念简单且非常有效的注意力模块。不同于现有的通道/空域注意力模块,该模块无需额外参数为特征图推导出3D注意力权值。具体来说,本文基于著名的神经科学理论提出优化能量函数以挖掘神经元的重要性。本文进一步针对该能量函数推导出一种快速解析解并表明:该解析解仅需不超过10行代码即可实现。该模块的另一个优势在于:大部分操作均基于所定义的能量函数选择,避免了过多的结构调整。最后,本文在不同的任务上对所提注意力模块的有效性、灵活性进行验证。

本文主要贡献包含以下几点:

  • 受启发于人脑注意力机制,本文提出一种3D注意力模块并设计了一种能量函数用于计算注意力权值;
  • 本文推导出了能量函数的解析解加速了注意力权值的计算并得到了一种轻量型注意力模块;
  • 将所提注意力嵌入到现有ConvNet中在不同任务上进行了灵活性与有效性的验证。
成为VIP会员查看完整内容
0
4

热门内容

This is the Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. Deep neural networks (DNNs) have undoubtedly brought great success to a wide range of applications in computer vision, computational linguistics, and AI. However, foundational principles underlying the DNNs' success and their resilience to adversarial attacks are still largely missing. Interpreting and theorizing the internal mechanisms of DNNs becomes a compelling yet controversial topic. This workshop pays a special interest in theoretic foundations, limitations, and new application trends in the scope of XAI. These issues reflect new bottlenecks in the future development of XAI.

0
0
下载
预览

最新论文

This is the Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. Deep neural networks (DNNs) have undoubtedly brought great success to a wide range of applications in computer vision, computational linguistics, and AI. However, foundational principles underlying the DNNs' success and their resilience to adversarial attacks are still largely missing. Interpreting and theorizing the internal mechanisms of DNNs becomes a compelling yet controversial topic. This workshop pays a special interest in theoretic foundations, limitations, and new application trends in the scope of XAI. These issues reflect new bottlenecks in the future development of XAI.

0
0
下载
预览
Top