论文标题
图像识别的双重互补动态卷积
Dual Complementary Dynamic Convolution for Image Recognition
论文作者
论文摘要
作为强大的引擎，香草卷积在各种计算机任务中促进了巨大的突破。但是，它通常遭受样本和内容不可知的问题，这限制了卷积神经网络（CNN）的表示能力。在本文中，我们在第一次模型中，场景的特征是个人与所有个人共享的本地空间自适应零件的结合，然后提出了一种新颖的两支分支双重互补动力卷积（DCDC）操作员，以灵活地处理这两种功能。 DCDC操作员克服了香草卷积和大多数现有动态卷积的局限性，它们仅捕获空间自适应特征，因此显着提高了CNN的表示能力。实验表明，基于DCDC操作员的重置（DCDC-RESNETS）显着超过了分类的香草重置和大多数最先进的动态卷积网络，以及下游任务，包括对象检测，实例检测，实例和全景分割任务，同时使用下部插槽和参数。
As a powerful engine, vanilla convolution has promoted huge breakthroughs in various computer tasks. However, it often suffers from sample and content agnostic problems, which limits the representation capacities of the convolutional neural networks (CNNs). In this paper, we for the first time model the scene features as a combination of the local spatial-adaptive parts owned by the individual and the global shift-invariant parts shared to all individuals, and then propose a novel two-branch dual complementary dynamic convolution (DCDC) operator to flexibly deal with these two types of features. The DCDC operator overcomes the limitations of vanilla convolution and most existing dynamic convolutions who capture only spatial-adaptive features, and thus markedly boosts the representation capacities of CNNs. Experiments show that the DCDC operator based ResNets (DCDC-ResNets) significantly outperform vanilla ResNets and most state-of-the-art dynamic convolutional networks on image classification, as well as downstream tasks including object detection, instance and panoptic segmentation tasks, while with lower FLOPs and parameters.
