论文标题
Dynet：加速卷积神经网络的动态卷积
DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
论文作者
论文摘要
卷积操作员是卷积神经网络（CNN）的核心，并且占据了最高的计算成本。为了提高CNN的效率，已经提出了许多方法来设计轻型网络或压缩模型。尽管已经提出了一些有效的网络结构，例如Mobilenet或Shufflenet，但我们发现卷积内核之间仍然存在冗余信息。为了解决这个问题，我们提出了一种新型的动态卷积方法，以根据图像内容自适应生成卷积内核。为了证明有效性，我们将动态卷积应用于多个最新的CNN。一方面，我们可以在保持性能的同时显着降低计算成本。对于ShuffLenetV2/Mobilenetv2/resnet18/resnet50，Dynet可以减少37.0/54.7/67.2/71.3％的拖鞋而不会损失准确性。另一方面，如果保持计算成本，则可以在很大程度上提高性能。基于体系结构Mobilenetv3-small/大型，Dynet在Imagenet上获得了70.3/77.1％的TOP-1精度，提高了2.9/1.9％。为了验证可伸缩性，我们还将Dynet应用于细分任务，结果表明，Dynet可以减少69.3％的失败，同时保持平均分段任务。
Convolution operator is the core of convolutional neural networks (CNNs) and occupies the most computation cost. To make CNNs more efficient, many methods have been proposed to either design lightweight networks or compress models. Although some efficient network structures have been proposed, such as MobileNet or ShuffleNet, we find that there still exists redundant information between convolution kernels. To address this issue, we propose a novel dynamic convolution method to adaptively generate convolution kernels based on image contents. To demonstrate the effectiveness, we apply dynamic convolution on multiple state-of-the-art CNNs. On one hand, we can reduce the computation cost remarkably while maintaining the performance. For ShuffleNetV2/MobileNetV2/ResNet18/ResNet50, DyNet can reduce 37.0/54.7/67.2/71.3% FLOPs without loss of accuracy. On the other hand, the performance can be largely boosted if the computation cost is maintained. Based on the architecture MobileNetV3-Small/Large, DyNet achieves 70.3/77.1% Top-1 accuracy on ImageNet with an improvement of 2.9/1.9%. To verify the scalability, we also apply DyNet on segmentation task, the results show that DyNet can reduce 69.3% FLOPs while maintaining Mean IoU on segmentation task.
