ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Ma, Ningning; Zhang, Xiangyu; Zheng, Haitao; Sun, Jian

doi:10.48550/arxiv.1807.11164

Cited by 143 publications

(145 citation statements)

References 19 publications

Supporting

Mentioning

145

Contrasting

Order By: Relevance

“…Non expansion. According to the paper of ShuffleNetV2 [16], we can learn that if the number of input feature maps and the number of output feature maps of convolutional layer are the same, computing speed will be maximized. Therefore, we don't expand the number of feature maps in our DFSEB Block.…”

Section: A Dfseb Blockmentioning

confidence: 99%

Efficient Convolutional Neural Network for Pest Recognition - ExquisiteNet

Zhou

2020

2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE)

View full text Add to dashboard Cite

Nowadays, due to the rapid population expansion, food shortage has become a critical issue. In order to stabilizing the food source production, preventing crops from being attacked by pests is very important. In generally, farmers use pesticides to kill pests, however, improperly using pesticides will also kill some insects which is beneficial to crops, such as bees. If the number of bees is too few, the supplement of food in the world will be in short. Besides, excessive pesticides will seriously pollute the environment. Accordingly, farmers need a machine which can automatically recognize the pests. Recently, deep learning is popular because its effectiveness in the field of image classification. In this paper, we propose a small and efficient model called ExquisiteNet to complete the task of recognizing the pests and we expect to apply our model on mobile devices. ExquisiteNet mainly consists of two blocks. One is double fusion with squeeze-and-excitation-bottleneck block (DFSEB block), and the other is max feature expansion block (ME block). ExquisiteNet only has 0.98M parameters and its computing speed is very fast almost the same as SqueezeNet. In order to evaluate our model's performance, we test our model on a benchmark pest dataset called IP102. Compared to many state-of-the-art models, such as ResNet101, ShuffleNetV2, MobileNetV3-large and EfficientNet etc., our model achieves higher accuracy, that is, 52.32% on the test set of IP102 without any data augmentation.

show abstract

Section: A Dfseb Blockmentioning

confidence: 99%

Efficient Convolutional Neural Network for Pest Recognition - ExquisiteNet

Zhou

2020

2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE)

View full text Add to dashboard Cite

show abstract

“…Group convolution [39] is an efficient convolution operation widely used in many efficient networks, it divides the input into independent groups and the kernels of each group share the same weight in order to reduce the number of parameters. Other efficient networks benefit from depth-wise convolution [22]- [25], [48] which is extreme case of group convolution. Recent works such as BiSeNet [36] and ICNet [37] also have better trade-off between accuracy and speed, but they are not easy to deploy and difficulty in migrating to other tasks and areas due to their complex structures.…”

Section: Related Workmentioning

confidence: 99%

“…1) Depth-wise Separable Convolutions: The depth-wise separable convolution is considered as key-module in recent efficient networks [22]- [25], it splits the full convolution operations into two independent operations, depth-wise convolution and point-wise convolution. In depth-wise convolution, the number of groups is equal to the number of feature maps, it means each kernel has single feature map in and single feature map out, and the shared weight kernels make the depth-wise Where 'DW' is depth-wise convolution, 'concat' is concatenation operation, 'MP' is Map-Pooling layer and 's' is layer stride.…”

Section: A Our Core Modulementioning

confidence: 99%

“…It is not benefit for scientific research specifically in remote sensing which also needs large memory allocation for high-resolution data with constraint computational resources. So besides accuracy, computation complexity, memory usage and inference speed are also essential metrics to measure the performance of an architecture [22]. Under this intuition, there is a variety of architectures are designed towards high accuracy and efficiency, such as MobileNet family [23], [24], ShuffleNet family [22], [25], ENet [26], ERFNet [27], EDANet [28] and so on.…”

Section: Introductionmentioning

confidence: 99%

“…So besides accuracy, computation complexity, memory usage and inference speed are also essential metrics to measure the performance of an architecture [22]. Under this intuition, there is a variety of architectures are designed towards high accuracy and efficiency, such as MobileNet family [23], [24], ShuffleNet family [22], [25], ENet [26], ERFNet [27], EDANet [28] and so on. The tradeoff between efficiency and accuracy becomes a key element for designing these efficient architectures.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images

Lin

Jing

Song³

et al. 2019

Preprint

View full text Add to dashboard Cite

Building footprint extraction from high-resolution aerial images is always an essential part of urban dynamic monitoring, planning and management. It has also been a challenging task in remote sensing research. In recent years, deep neural networks have made great achievement in improving accuracy of building extraction from remote sensing imagery. However, most of existing approaches usually require large amount of parameters and floating point operations for high accuracy, it leads to high memory consumption and low inference speed which are harmful to research. In this paper, we proposed a novel efficient network named ESFNet which employs separable factorized residual block and utilizes the dilated convolutions, aiming to preserve slight accuracy loss with low computational cost and memory consumption. Our ESFNet obtains a better trade-off between accuracy and efficiency, it can run at over 100 FPS on single Tesla V100, requires 6x fewer FLOPs and has 18x fewer parameters than state-of-the-art real-time architecture ERFNet while preserving similar accuracy without any additional context module, post-processing and pre-trained scheme. We evaluated our networks on WHU Building Dataset and compared it with other state-of-the-art architectures. The result and comprehensive analysis show that our networks are benefit for efficient remote sensing researches, and the idea can be further extended to other areas. The code is public available at: https://github.com/mrluin/ESFNet-Pytorch

show abstract

Navigation line extraction algorithm for corn spraying robot based on YOLOv8s‐CornNet

Guo,

Diao,

Zhao

et al. 2024

Journal of Field Robotics

View full text Add to dashboard Cite

The continuous and close combination of artificial intelligence technology and agriculture promotes the rapid development of smart agriculture, among which the agricultural robot navigation line recognition algorithm based on deep learning has achieved great success in detection accuracy and detection speed. However, there are still many problems, such as the large size of the algorithm is difficult to deploy in hardware equipment, and the accuracy and speed of crop row detection in real farmland environment are low. To solve the above problems, this paper proposed a navigation line extraction algorithm for corn spraying robot based on YOLOv8s‐CornNet. First, the Convolution (Conv) module and C2f module of YOLOv8s network are replaced with Depthwise Convolution (DWConv) module and PP‐LCNet module respectively to reduce the parameters (Params) and giga floating‐point operations per second of the network, so as to achieve the purpose of network lightweight. Second, to reduce the precision loss caused by network lightweight, the spatial pyramid pooling fast module in the backbone network is changed to atrous spatial pyramid pooling faster module to improve the accuracy of network feature extraction. Meanwhile, normalization‐based attention module is introduced into the network to improve the network's attention to corn plants. Then the corn plant was located by using the midpoint of the corn plant detection box. Finally, the least square method is used to extract the corn crop row line, and the middle line of the corn crop row line is the navigation line of the corn spraying robot. From the experimental results, it can be seen that the navigation line extraction algorithm proposed in this paper ensures both the real‐time and accuracy of the navigation line extraction of the corn spraying robot, which contributes to the development of the visual navigation technology of agricultural robots.

show abstract

ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design

Cited by 143 publications

References 19 publications

Efficient Convolutional Neural Network for Pest Recognition - ExquisiteNet

Efficient Convolutional Neural Network for Pest Recognition - ExquisiteNet

ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images

Navigation line extraction algorithm for corn spraying robot based on YOLOv8s‐CornNet

Contact Info

Product

Resources

About