论文标题
通过有效的扩张搜索开始卷卷
Inception Convolution with Efficient Dilation Search
论文作者
论文摘要
作为标准卷积的变体，扩张的卷积可以控制有效的接受场并处理对象的大规模差异，而无需引入额外的计算成本。为了充分探索扩张卷积的潜力，我们提出了一种新型的扩张卷积（称为Inception卷积），其中卷积操作在不同轴，通道和层之间具有独立的扩张模式。为了根据数据开发一种实用方法来学习复杂的结构卷积，开发了一种简单但有效的搜索算法，称为有效扩张优化（EDO）。基于统计优化，EDO方法以低成本的方式运行，并且将其应用于大型数据集时非常快。经验结果验证了我们的方法可以达到图像识别，对象检测，实例分割，人类检测和人姿势估计的一致性增长。例如，通过简单地将Resnet-50骨干线中的3x3标准卷积替换为Inception卷积，我们将在MS Coco上显着将更快的R-CNN的AP从36.4％提高到39.2％。
As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computational costs. To fully explore the potential of dilated convolution, we proposed a new type of dilated convolution (referred to as inception convolution), where the convolution operations have independent dilation patterns among different axes, channels and layers. To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed. Based on statistical optimization, the EDO method operates in a low-cost manner and is extremely fast when it is applied on large scale datasets. Empirical results validate that our method achieves consistent performance gains for image recognition, object detection, instance segmentation, human detection, and human pose estimation. For instance, by simply replacing the 3x3 standard convolution in the ResNet-50 backbone with inception convolution, we significantly improve the AP of Faster R-CNN from 36.4% to 39.2% on MS COCO.
