4 papers
Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors
Hao Yu, Zhaoning Zhang, Zheng Qin +4
Modern object detectors usually suffer from low accuracy issues, as foregrounds always drown in tons of backgrounds and become hard examples during training. Compared with those pr…
Diagonalwise Refactorization: An Efficient Training Method for Depthwise Convolutions
Zheng Qin, Zhaoning Zhang, Dongsheng Li +2
Depthwise convolutions provide significant performance benefits owing to the reduction in both parameters and mult-adds. However, training depthwise convolution layers with GPUs is…
Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications
Zheng Qin, Zhaoning Zhang, Shiqing Zhang +2
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compare…
FD-MobileNet: Improved MobileNet with a Fast Downsampling Strategy
Zheng Qin, Zhaoning Zhang, Xiaotao Chen +1
We present Fast-Downsampling MobileNet (FD-MobileNet), an efficient and accurate network for very limited computational budgets (e.g., 10-140 MFLOPs). Our key idea is applying an a…