ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Ningning Ma,Xiangyu Zhang,Hai-Tao Zheng,Jian Sun +3 more
- pp 122-138
TLDR
ShuffleNet V2 as discussed by the authors proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs, based on a series of controlled experiments, and derives several practical guidelines for efficient network design.Abstract:
Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the other factors such as memory access cost and platform characterics. Thus, this work proposes to evaluate the direct metric on the target platform, beyond only considering FLOPs. Based on a series of controlled experiments, this work derives several practical guidelines for efficient network design. Accordingly, a new architecture is presented, called ShuffleNet V2. Comprehensive ablation experiments verify that our model is the state-of-the-art in terms of speed and accuracy tradeoff.read more
Citations
More filters
Posted Content
YOLOv4: Optimal Speed and Accuracy of Object Detection
TL;DR: This work uses new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, C mBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.
Proceedings Article
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Mingxing Tan,Quoc V. Le +1 more
TL;DR: EfficientNet-B7 as discussed by the authors proposes a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient, which achieves state-of-the-art accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference.
Proceedings ArticleDOI
CSPNet: A New Backbone that can Enhance Learning Capability of CNN
TL;DR: Cross Stage Partial Network (CSPNet) as discussed by the authors integrates feature maps from the beginning and the end of a network stage to mitigate the problem of duplicate gradient information within network optimization.
Proceedings ArticleDOI
MnasNet: Platform-Aware Neural Architecture Search for Mobile
TL;DR: In this article, the authors propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporates model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.
Journal ArticleDOI
Res2Net: A New Multi-Scale Backbone Architecture
TL;DR: Res2Net as mentioned in this paper constructs hierarchical residual-like connections within one single residual block to represent multi-scale features at a granular level and increases the range of receptive fields for each network layer.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.