Recent studies on mobile network design have demonstrated the remarkable effectiveness
of channel attention (eg, the Squeeze-and-Excitation attention) for lifting model performance …

The inverted residual block is dominating architecture design for mobile networks recently. It
changes the classic residual bottleneck by introducing two design rules: learning inverted …

This paper aims at addressing the problem of substantial performance degradation at
extremely low computational cost (eg 5M FLOPs on ImageNet classification). We found that …

Lightweight super resolution networks have extremely importance for real-world
applications. In recent years several SR deep learning approaches with outstanding …

We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for
regular convolutional layers, which is a plug-and-play module to improve the performance …

Designing a lightweight and robust portrait segmentation algorithm is an important task for a
wide range of face applications. However, the problem has been considered as a subset of …

We propose a general method to train a single convolutional neural network which is
capable of switching image resolutions at inference. Thus the running speed can be …

Designing light-weight CNN models with little parameters and Flops is a prominent research
concern. However, three significant issues persist in the current light-weight CNNs: i) the …

To improve accuracy of the MobileNet network, a new lightweight deep neural network is
designed based on the MobileNetV2 network. Firstly, it modifies the network depth of …

The pumping unit is the most important lifting equipment in the rod pumping system, which
transmits ground power to the downhole pump through its sucker rod. Trajectory …