Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i. e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet.
In particular, we propose a novel joint-training framework to train plain CNN by leveraging the gradients of the ResNet counterpart.
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
This paper expands the strength of deep convolutional neural networks (CNNs) to the pedestrian attribute recognition problem by devising a novel attribute aware pooling algorithm.
Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks.
Learning portable neural networks is very essential for computer vision for the purpose that pre-trained heavy deep models can be well applied on edge devices such as mobile phones and micro sensors.