activity
20152022
most citedA Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges

2.7k citations · 5.1k across the 51 of their papers we have counts for

collaborators
Showing 2021Show all

8 papers · 1 filter

cs.CR2021

Defending against Model Stealing via Verifying Embedded External Features

Yiming Li, Linghui Zhu, Xiaojun Jia +3

Obtaining a well-trained model involves expensive data collection and training procedures, therefore the model is a valuable intellectual property. Recent studies revealed that adv…

cs.CV2021★ 69 cited

Boosting Fast Adversarial Training with Learnable Adversarial Initialization

Xiaojun Jia, Yong Zhang, Baoyuan Wu +2

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face…

cs.CV2021★ 7 cited

An Effective and Robust Detector for Logo Detection

Xiaojun Jia, Huanqian Yan, Yonglin Wu +3

In recent years, intellectual property (IP), which represents literary, inventions, artistic works, etc, gradually attract more and more people's attention. Particularly, with the…

cs.LG2021★ 1 cited

Learning with Multiclass AUC: Theory and Algorithms

Zhiyong Yang, Qianqian Xu, Shilong Bao +2

The Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. The vast majority of existing AUC-optimization-b…

cs.LG2021★ 24 cited

Poisoning Attack against Estimating from Pairwise Comparisons

Ke Ma, Qianqian Xu, Jinshan Zeng +2

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranki…

cs.CV2021★ 3 cited

Arbitrarily Shaped Scene Text Detection: A Decade of Advances and Systematic Analysis

Pengwen Dai, Feiyang He, Chaolang Li +3

Scene text detection has become an important research area in computer vision. However, dynamic changes in scenes and the complex diversity of text appearances make accurate scene…

cs.CV2021★ 12 cited

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

Binyi Su, Zhong Zhou, Haiyong Chen +1

Solar cell electroluminescence (EL) defect segmentation is an interesting and challenging topic. Many methods have been proposed for EL defect detection, but these methods are stil…

cs.CV2021★ 83 cited

A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation

Shuren Qi, Yushu Zhang, Chao Wang +2

Image representation is an important topic in computer vision and pattern recognition. It plays a fundamental role in a range of applications towards understanding visual contents.…