TensorProjection 层：深度神经网络中一种基于张量的降维方法
TensorProjection Layer: A Tensor-Based Dimension Reduction Method in Deep Neural Networks
AI总结：
本文提出 TensorProjection 层，通过可学习的按模态投影对张量特征进行降维，可替代池化或卷积层用于图像汇总和通道压缩，并在医学图像分类与分割任务中优于传统下采样方法。
摘要：
在本文中，我们提出了一种专门针对深度神经网络中张量结构特征数据的降维方法。该方法实现为一个隐藏层，称为 TensorProjection 层，通过按模态投影将输入张量转换为维度降低的输出张量。投影方向被视为该层的模型参数，并在模型训练过程中进行优化。我们的方法可以作为池化层的替代方案，用于汇总图像数据，也可以作为卷积层的一种技术，用于减少通道数量。我们在医学图像分类和分割等任务上进行了实验，将 TensorProjection 层集成到常用的基线架构中，以评估其有效性。数值实验表明，所提出的方法在我们的任务中可以优于传统的下采样方法（如池化层），这表明它是一种有前景的特征汇总替代方案。
英文摘要：
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.
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。
