Convolutional neural networks (CNNs) have been the source of recent breakthroughs in many vision tasks. Feature pooling layers are being widely used in CNNs to reduce the spatial dimensions of the feature maps of the hidden layers. This gives CNNs the property of spatial invariance and also results in speed-up and reduces over-fitting. However, this also causes significant information loss. All existing feature pooling layers follow a one-step procedure for spatial pooling, which affects the overall performance due to significant information loss. Not much work has been done to do efficient feature pooling operation in CNNs. To reduce the loss of information at this critical operation of the CNNs, we propose a new EDS layer (Expansion Downsampling learnable-Scaling) to replace the existing pooling mechanism. We propose a two-step procedure to minimize the information loss by increasing the number of channels in pooling operation. We also use feature scaling in the proposed EDS layer to highlight the most relevant channels/feature-maps. Our results show a significant improvement over the generally used pooling methods such as MaxPool, AvgPool, and StridePool (strided convolutions with stride > 1). We have done the experiments on image classification and object detection task. ResNet-50 with our proposed EDS layer has performed comparably to ResNet-152 with stride pooling on the ImageNet dataset.

卷积神经网络（CNN）是许多视觉任务中最新突破的源头。在CNN中，要素池层已被广泛使用，以减小隐藏层要素图的空间尺寸。这使CNN具有空间不变性的特性，还可以加快速度并减少过度拟合。但是，这也会导致大量的信息丢失。所有现有的要素池层都遵循一个一步的空间池过程，由于大量信息丢失，这会影响整体性能。在CNN中进行高效的特征池操作尚未做很多工作。为了减少在CNN的这一关键操作过程中丢失的信息，我们提出了一个新的EDS层（扩展下采样可学习缩放）来替代现有的合并机制。我们提出了一个两步过程，以通过增加池化操作中的通道数来最大程度地减少信息丢失。我们还在提议的EDS层中使用特征缩放来突出显示最相关的通道/特征图。我们的结果表明，与常用的合并方法（例如MaxPool，AvgPool和StridePool（步长> 1的卷积卷积））相比，有了显着的改进。我们已经完成了图像分类和目标检测任务的实验。带有我们建议的EDS层的ResNet-50与ImageNet数据集上的步幅池具有与ResNet-152相当的性能。我们的结果表明，与常用的合并方法（例如MaxPool，AvgPool和StridePool（步长> 1的卷积卷积））相比，有了显着的改进。我们已经完成了图像分类和目标检测任务的实验。带有我们建议的EDS层的ResNet-50与ImageNet数据集上的步幅池具有与ResNet-152相当的性能。我们的结果表明，与常用的合并方法（例如MaxPool，AvgPool和StridePool（步长> 1的卷积卷积））相比，有了显着的改进。我们已经完成了图像分类和目标检测任务的实验。带有我们建议的EDS层的ResNet-50与ImageNet数据集上的步幅池具有与ResNet-152相当的性能。