论文标题
缩放宽剩余网络以进行全景分段
Scaling Wide Residual Networks for Panoptic Segmentation
论文作者
论文摘要
宽剩余网络（宽元网络）是剩余网络（RESNET）的浅但广泛的模型变体，通过堆叠少量具有较大通道尺寸的残差块，在多个密集的预测任务上表现出出色的性能。但是，自提议以来，多年来，广泛的建筑几乎没有发展。在这项工作中，我们重新审视其架构设计，以实现最近具有挑战性的全盘细分任务，该任务旨在统一语义细分和实例分割。通过将简单有效的挤压和可切换性卷积纳入宽元素来获得基线模型。通过调整宽度（即通道大小）和深度（即层数），进一步扩展其网络容量，从而导致旋转家族（用于扩展宽剩余网络的缩写）。我们证明，这样一个简单的缩放方案，再加上网格搜索，标识了几个旋转组，可以在快速模型制度和强型模型制度中显着提高全盘细分数据集中的最新性能。
The Wide Residual Networks (Wide-ResNets), a shallow but wide model variant of the Residual Networks (ResNets) by stacking a small number of residual blocks with large channel sizes, have demonstrated outstanding performance on multiple dense prediction tasks. However, since proposed, the Wide-ResNet architecture has barely evolved over the years. In this work, we revisit its architecture design for the recent challenging panoptic segmentation task, which aims to unify semantic segmentation and instance segmentation. A baseline model is obtained by incorporating the simple and effective Squeeze-and-Excitation and Switchable Atrous Convolution to the Wide-ResNets. Its network capacity is further scaled up or down by adjusting the width (i.e., channel size) and depth (i.e., number of layers), resulting in a family of SWideRNets (short for Scaling Wide Residual Networks). We demonstrate that such a simple scaling scheme, coupled with grid search, identifies several SWideRNets that significantly advance state-of-the-art performance on panoptic segmentation datasets in both the fast model regime and strong model regime.
