Xinyu Tian
21 Papers
2 Citations
Xinyu Tian is an academic researcher. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 3, co-authored 5 publications.
Chat about Author
Papers
A Full Stage Data Augmentation Method in Deep Convolutional Neural Network for Natural Image Classification
TL;DR: This paper proposes a full stage data augmentation framework to improve the accuracy of deep convolutional neural networks, which can also play the role of implicit model ensemble without introducing additional model training costs.
PAC-Bayesian framework based drop-path method for 2D discriminative convolutional network pruning
TL;DR: This paper introduces a novel pruning method named Drop-path to reduce model parameters of 2D deep CNNs for the first time based on the generalization error boundary, and observes that the convolutional kernels themselves become sparse, rather than some being removed directly.
94
DL-PR: Generalized automatic modulation classification method based on deep learning with priori regularization
TL;DR: In this paper , a priori regularization method in deep learning (DL-PR) is proposed for guiding loss optimization during model training process to improve automatic modulation classification (AMC).
61
Layer-wise learning based stochastic gradient descent method for the optimization of deep convolutional neural network
TL;DR: This paper proposes LLb-SGD, a layer-wise learning based stochastic gradient descent method for optimizing deep CNNs, which adapts learning rates using a cross-media propagation mechanism, ensuring convergence and robustness across various network architectures and datasets.
59
Application of Wavelet-Packet Transform Driven Deep Learning Method in PM2.5 Concentration Prediction: A Case Study of Qingdao, China
TL;DR: Wang et al. as discussed by the authors proposed a wavelet-packet transform (WPT) driven deep learning model to predict the hourly PM2.5 concentration and verify its effectiveness when applied to Qingdao, China.
52