EfficientNet explained

EfficientNet is a family of convolutional neural networks (CNNs) for computer vision published by researchers at Google AI in 2019. Its key innovation is compound scaling, which uniformly scales all dimensions of depth, width, and resolution using a single parameter.

EfficientNet models have been adopted in various computer vision tasks, including image classification, object detection, and segmentation.

Compound scaling

EfficientNet introduces compound scaling, which, instead of scaling one dimension of the network at a time, such as depth (number of layers), width (number of channels), or resolution (input image size), uses a compound coefficient

to scale all three dimensions simultaneously. Specifically, given a baseline network, the depth, width, and resolution are scaled according to the following equations:subject to and . The condition is such that increasing by a factor of would increase the total FLOPs of running the network on an image approximately times. The hyperparameters , , and are determined by a small grid search. The original paper suggested 1.2, 1.1, and 1.15, respectively.

Architecturally, they optimized the choice of modules by neural architecture search (NAS), and found that the inverted bottleneck convolution (which they called MBConv) used in MobileNet worked well.

The EfficientNet family is a stack of MBConv layers, with shapes determined by the compound scaling. The original publication consisted of 8 models, from EfficientNet-B0 to EfficientNet-B7, with increasing model size and accuracy. EfficientNet-B0 is the baseline network, and subsequent models are obtained by scaling the baseline network by increasing

.

Variants

EfficientNet has been adapted for fast inference on edge TPUs^[1] and centralized TPU or GPU clusters by NAS.

EfficientNet V2 was published in June 2021. The architecture was improved by further NAS search with more types of convolutional layers. It also introduced a training method, which progressively increases image size during training, and uses regularization techniques like dropout, RandAugment,^[2] and Mixup. The authors claim this approach mitigates accuracy drops often associated with progressive resizing.

See also

• Convolutional neural network
• SqueezeNet
• MobileNet
• You Only Look Once

References

1. Web site: August 6, 2019 . EfficientNet-EdgeTPU: Creating Accelerator-Optimized Neural Networks with AutoML . 2024-10-18 . research.google . en.
2. Cubuk . Ekin D. . Zoph . Barret . Shlens . Jonathon . Le . Quoc V. . 2020 . Randaugment: Practical Automated Data Augmentation With a Reduced Search Space . 702–703. 1909.13719 .

External links

• EfficientNet: Improving Accuracy and Efficiency through AutoML and Model Scaling (Google AI Blog)