SPGNet: Serial and Parallel Group Network
- 1 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24, 2804-2814
- https://doi.org/10.1109/TMM.2021.3088639
Abstract
Neural-network Processing Units (NPU), which specializes in the acceleration of deep neural networks (DNN), is of great significance to latency-sensitive areas like robotics or edge computing. However, there are few works focusing on the network design for NPU in recent studies. Most of the popular lightweight structures (e.g. MobileNet) are designed with depthwise convolution, which has less computation in theory but is not friendly to existing hardwares, and the speed tested on NPU is not always satisfactory. Even under similar FLOPs (the number of multiply-accumulates), vanilla convolution operation is always faster than depthwise one. In this paper, we will propose a novel architecture named Serial and Parallel Group Network (SPGNet), which can capture discriminative multi-scale information and at the same time keep the structure compact. Extensive evaluations have been conducted on different computer vision tasks, e.g. image classification (CIFAR and ImageNet), object detection (PASCAL VOC and MS COCO) and person re-identification (Market-1501 and DukeMTMC-ReID). The experimental results show that our proposed SPGNet can achieve comparable performance with the state-of-the-art networks while the speed is 120% faster than MobileNetV2 under similar FLOPS and over 300% faster than GhostNet with similar accuracy on NPU.Funding Information
- National Natural Science Foundation of China (61772407, 61732008)
- Meituan
This publication has 48 references indexed in Scilit:
- Learning Discriminative Features with Multiple Granularities for Person Re-IdentificationPublished by Association for Computing Machinery (ACM) ,2018
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)Published by Springer Science and Business Media LLC ,2018
- GLAD: Global–Local-Alignment Descriptor for Scalable Person Re-IdentificationIEEE Transactions on Multimedia, 2018
- Interleaved Group ConvolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Densely Connected Convolutional NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Xception: Deep Learning with Depthwise Separable ConvolutionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Aggregated Residual Transformations for Deep Neural NetworksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Re-ranking Person Re-identification with k-Reciprocal EncodingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2017
- Deep Residual Learning for Image RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016
- The Cityscapes Dataset for Semantic Urban Scene UnderstandingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2016