DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks

TL;DR

This paper introduces DyNet, a dynamic convolution method that adaptively generates kernels based on image content, significantly reducing computation costs while maintaining or improving CNN performance across various tasks.

Contribution

The paper proposes a novel dynamic convolution approach that reduces redundancy in kernels and enhances efficiency and accuracy in CNNs, outperforming existing lightweight models.

Findings

Reduces FLOPs by up to 71.3% without accuracy loss.

Improves Top-1 accuracy on ImageNet by up to 2.9%.

Maintains segmentation performance while reducing FLOPs by 69.3%.

Abstract

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.