|
|
|
|
|
Jie Wang, Jie Yang, Jiafan He and Dongliang Peng
Semi-supervised learning has been proven to be effective in utilizing unlabeled samples to mitigate the problem of limited labeled data. Traditional semi-supervised learning methods generate pseudo-labels for unlabeled samples and train the classifier us...
ver más
|
|
|
|
|
|
|
|
|
|
|
Xing Wu, Yifan Jin, Jianjia Wang, Quan Qian and Yike Guo
Large-scale automatic speech recognition model has achieved impressive performance. However, huge computational resources and massive amount of data are required to train an ASR model. Knowledge distillation is a prevalent model compression method which ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Yan Zhang, Shupeng He, Shiyun Wa, Zhiqi Zong and Yunling Liu
Apple flower detection is an important project in the apple planting stage. This paper proposes an optimized detection network model based on a generative module and pruning inference. Due to the problems of instability, non-convergence, and overfitting ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Fan Yang, Deming Yang, Zhiming He, Yuanhua Fu and Kui Jiang
Upgrading ordinary streetlights to smart streetlights to help monitor traffic flow is a low-cost and pragmatic option for cities. Fine-grained classification of vehicles in the sight of smart streetlights is essential for intelligent transportation and s...
ver más
|
|
|
|
|
|