论文标题
MORPHPOOL：有效的非线性合并和CNN中的不致密
MorphPool: Efficient Non-linear Pooling & Unpooling in CNNs
论文作者
论文摘要
合并本质上是数学形态领域的操作，最大合并为有限的特殊情况。更通用的变形设置极大地扩展了建立神经网络的工具集。除了汇总操作外，用于像素级预测的编码器 - 码头网络还需要不解决。通常，将非冷冻与卷积或反卷积结合起来进行上采样。但是，使用其形态学特性，可以推广和改进不致密。对两项任务和三个大规模数据集进行了广泛的实验表明，形态的汇集和不致密会导致在大量降低的参数计数下提高预测性能。
Pooling is essentially an operation from the field of Mathematical Morphology, with max pooling as a limited special case. The more general setting of MorphPooling greatly extends the tool set for building neural networks. In addition to pooling operations, encoder-decoder networks used for pixel-level predictions also require unpooling. It is common to combine unpooling with convolution or deconvolution for up-sampling. However, using its morphological properties, unpooling can be generalised and improved. Extensive experimentation on two tasks and three large-scale datasets shows that morphological pooling and unpooling lead to improved predictive performance at much reduced parameter counts.
