Yueru Chen

Yueru Chen

Auto-generated profile, based on publicly available information

Yueru Chen

University of Southern California

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2020 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
YCYueru Chen
Yueru Chen
CKC.-C. Jay Kuo
C.-C. Jay Kuo

1 July 2017 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Open access
XPXiaqing Pan
Xiaqing Pan
YCYueru Chen
Yueru Chen
CKC.-C. Jay Kuo
C.-C. Jay Kuo

2 December 2018 in arXiv
Verified
Preprint
Open access
PDF file
APAbhishek Panigrahi
Abhishek Panigrahi
YCYueru Chen
Yueru Chen
CKC.-C. Jay Kuo
C.-C. Jay Kuo
We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this work. By analyzing the mean and variance behavior of the input and the gradient in the forward and backward passes through the BN and residual branches, respectively, we show that they work together to confine the gradient variance to a certain range across residual blocks in backpropagation. As a result, the gradient vanishing/explosion problem is avoided. We also show the relative importance of batch normalization w.r.t. the residual branches in residual networks.

25 May 2019
Verified
Book Chapter
Closed access
PDF file
YWYe Wang
Ye Wang
JCJongmoo Choi
Jongmoo Choi
YCYueru Chen
Yueru Chen
QHQin Huang
Qin Huang
SLSiyang Li
Siyang Li
CKC.-C. Jay Kuo
C.-C. Jay Kuo

4 December 2017 in arXiv
Verified
Preprint
Open access
PDF file
YCYueru Chen
Yueru Chen
PAPranav Aggarwal
Pranav Aggarwal
JCJongmoo Choi
Jongmoo Choi
CKC.-C. Jay Kuo
C.-C. Jay Kuo
A drone monitoring system that integrates deep-learning-based detection and tracking modules is proposed in this work. The biggest challenge in adopting deep learning methods for drone detection is the limited amount of training drone images. To address this issue, we develop a model-based drone augmentation technique that automatically generates drone images with a bounding box label on drone's location. To track a small flying drone, we utilize the residual information between consecutive image frames. Finally, we present an integrated detection and tracking system that outperforms the performance of each individual module containing detection or tracking only. The experiments show that, even being trained on synthetic data, the proposed system performs well on real world drone images with complex background. The USC drone detection and tracking dataset with user labeled bounding boxes is available to the public.

17 September 2019 in arXiv
Verified
Preprint
Open access
PDF file
YCYueru Chen
Yueru Chen
CKC.-C. Jay Kuo
C.-C. Jay Kuo
A new machine learning methodology, called successive subspace learning (SSL), is introduced in this work. SSL contains four key ingredients: 1) successive near-to-far neighborhood expansion; 2) unsupervised dimension reduction via subspace approximation; 3) supervised dimension reduction via label-assisted regression (LAG); and 4) feature concatenation and decision making. An image-based object classification method, called PixelHop, is proposed to illustrate the SSL design. It is shown by experimental results that the PixelHop method outperforms the classic CNN model of similar model complexity in three benchmarking datasets (MNIST, Fashion MNIST and CIFAR-10). Although SSL and deep learning (DL) have some high-level concept in common, they are fundamentally different in model formulation, the training process and training complexity. Extensive discussion on the comparison of SSL and DL is made to provide further insights into the potential of SSL.