Yurong Chen

Yurong Chen

Auto-generated profile, based on publicly available information

Yurong Chen

Intel Labs China

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

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

Representative Publications

View All Publications
11 June 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
ZSZhiqiang Shen
Zhiqiang Shen
ZLZhuang Liu
Zhuang Liu
JLJianguo Li
Jianguo Li
YJYu-Gang Jiang
Yu-Gang Jiang
YCYurong Chen
Yurong Chen
XXXiangyang Xue
Xiangyang Xue
We propose Deeply Supervised Object Detectors (DSOD), an object detection framework that can be trained from scratch. Recent advances in object detection heavily depend on the off-the-shelf models pre-trained on large-scale classification datasets like ImageNet and OpenImage. However, one problem is that adopting pre-trained models from classification to detection task may incur learning bias due to the different objective function and diverse distributions of object categories. Techniques like fine-tuning on detection task could alleviate this issue to some extent but are still not fundamental. Furthermore, transferring these pre-trained models cross discrepant domains will be more difficult (e.g., from RGB to depth images). Thus, a better solution to handle these critical problems is to train object detectors from scratch, which motivates our proposed method. In DSOD, we contribute a set of design principles for learning object detectors from scratch. One of the key principles is the deep supervision, enabled by layer-wise dense connections in both backbone networks and prediction layers, plays a critical role in learning good detectors from scratch. We evaluate our method on PASCAL VOC 2007, 2012 and COCO datasets. DSOD achieves consistently better results than the state-of-the-art methods with much more compact models.

29 December 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
JZJiahui Zhang
Jiahui Zhang
DSDawei Sun
Dawei Sun
ZLZixin Luo
Zixin Luo
AYAnbang Yao
Anbang Yao
HCHongkai Chen
Hongkai Chen
Hongen LiaoHongen Liao
Hongen Liao
Establishing correct correspondences between two images should consider both local and global spatial context. Given putative correspondences of feature points in two views, in this paper, we propose Order-Aware Network, which infers the probabilities of correspondences being inliers and regresses the relative pose encoded by the essential or fundamental matrix. Specifically, this proposed network is built hierarchically and comprises three operations. First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix. These clusters are in canonical order and invariant to input permutations. Next, the clusters are spatially correlated to encode the global context of correspondences. After that, the context-encoded clusters are interpolated back to the original size and position to build a hierarchical architecture. We intensively experiment on both outdoor and indoor datasets. The accuracy of the two-view geometry and correspondences are significantly improved over the state-of-the-arts. Besides, based on the proposed method and advanced local feature, we won the first place in CVPR 2019 image matching workshop challenge and also achieve state-of-the-art results in the Visual Localization benchmark. Code is available at https://github.com/zjhthu/OANet.

3 July 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YGYiwen Guo
Yiwen Guo
LCLong Chen
Long Chen
YCYurong Chen
Yurong Chen
CZChangshui Zhang
Changshui Zhang
This paper analyzes regularization terms proposed recently for improving the adversarial robustness of deep neural networks (DNNs), from a theoretical point of view. Specifically, we study possible connections between several effective methods, including input-gradient regularization, Jacobian regularization, curvature regularization, and a cross-Lipschitz functional. We investigate them on DNNs with general rectified linear activations, which constitute one of the most prevalent families of models for image classification and a host of other machine learning applications. We shed light on essential ingredients of these regularizations and re-interpret their functionality. Through the lens of our study, more principled and efficient regularizations can possibly be invented in the near future.

3 November 2022
Verified
Book Chapter
Closed access
PDF file
XLXiaoqi Li
Xiaoqi Li
JLJiaming Liu
Jiaming Liu
SWShizun Wang
Shizun Wang
CLCheng Lyu
Cheng Lyu
MLMing Lu
Ming Lu
SZShanghang Zhang
Shanghang Zhang

3 March 2024 in Food Control
Verified
Journal Article
Closed access
JSJingfei Shen
Jingfei Shen
TLTiehan Li
Tiehan Li
YCYurong Chen
Yurong Chen
HZHuan Zhou
Huan Zhou
SDShuai Dong
Shuai Dong
LLLuqing Li
Luqing Li

16 November 2007 in Intel Technology Journal
Verified
Journal Article
Closed access
YCYurong Chen
Yurong Chen
Intel designs and builds the essential technologies that serve as the foundation for the world’s computing devices.