Dynamic Multi-path Neural Network
This addresses efficiency issues for resource-constrained applications in computer vision, offering a novel approach beyond existing depth-only methods.
The paper tackles the problem of high computational cost in deep neural networks by proposing Dynamic Multi-path Neural Network (DMNN), which dynamically selects inference paths based on width and depth, achieving a 45.1% FLOPs reduction compared to ResNet-101 while maintaining or improving accuracy on ImageNet and CIFAR-100.
Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications. Existing methods usually choose to execute or skip an entire specific layer, which can only alter the depth of the network. In this paper, we propose a novel method called Dynamic Multi-path Neural Network (DMNN), which provides more path selection choices in terms of network width and depth during inference. The inference path of the network is determined by a controller, which takes into account both previous state and object category information. The proposed method can be easily incorporated into most modern network architectures. Experimental results on ImageNet and CIFAR-100 demonstrate the superiority of our method on both efficiency and overall classification accuracy. To be specific, DMNN-101 significantly outperforms ResNet-101 with an encouraging 45.1% FLOPs reduction, and DMNN-50 performs comparably to ResNet-101 while saving 42.1% parameters.