论文标题
张力量注射层：深神经网络中的基于张量的降低方法
TensorProjection Layer: A Tensor-Based Dimension Reduction Method in Deep Neural Networks
论文作者
论文摘要
在本文中，我们提出了一种针对深神经网络中张量结构的特征数据设计的尺寸缩小方法。该方法被实现为隐藏层，称为张量投影层，该层将输入张量转换为输出张量，并通过模式下的投影降低了尺寸。投影方向被视为层的模型参数，并在模型训练期间进行了优化。我们的方法可以用作汇总图像数据的汇总层的替代方法，或者将卷积层作为减少通道数量的技术。我们对诸如医学图像分类和分割等任务进行实验，将张力注射层整合到常用的基线体系结构中以评估其有效性。数值实验表明，所提出的方法可以优于传统的倒数采样方法，例如在我们的任务中汇总层，这表明它是特征摘要的有希望的替代方法。
In this paper, we propose a dimension reduction method specifically designed for tensor-structured feature data in deep neural networks. The method is implemented as a hidden layer, called the TensorProjection layer, which transforms input tensors into output tensors with reduced dimensions through mode-wise projections. The projection directions are treated as model parameters of the layer and are optimized during model training. Our method can serve as an alternative to pooling layers for summarizing image data, or to convolutional layers as a technique for reducing the number of channels. We conduct experiments on tasks such as medical image classification and segmentation, integrating the TensorProjection layer into commonly used baseline architectures to evaluate its effectiveness. Numerical experiments indicate that the proposed method can outperform traditional downsampling methods, such as pooling layers, in our tasks, suggesting it as a promising alternative for feature summarization.
