no code implementations • 28 Sep 2023 • Xiaogang Jia, Songlei Jian, Yusong Tan, Yonggang Che, Wei Chen, Zhengfa Liang
With a simple yet efficient gating mechanism, our proposed method achieves fast and accurate depth completion without the need for additional branches or post-processing steps.
1 code implementation • 25 Jul 2023 • Hongzuo Xu, Yijie Wang, Guansong Pang, Songlei Jian, Ning Liu, Yongjun Wang
anomaly contamination.
Semi-supervised Anomaly Detection Supervised Anomaly Detection +1
2 code implementations • 25 May 2023 • Hongzuo Xu, Yijie Wang, Juhui Wei, Songlei Jian, Yizhou Li, Ning Liu
Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals.
1 code implementation • 25 Jul 2022 • Hongzuo Xu, Yijie Wang, Songlei Jian, Qing Liao, Yongjun Wang, Guansong Pang
To tackle these problems, this paper proposes calibrated one-class classification for anomaly detection, realizing contamination-tolerant, anomaly-informed learning of data normality via uncertainty modeling-based calibration and native anomaly-based calibration.
no code implementations • 30 Apr 2021 • Zhiyue Wu, Hongzuo Xu, Guansong Pang, Fengyuan Yu, Yijie Wang, Songlei Jian, Yongjun Wang
DRAM failure prediction is a vital task in AIOps, which is crucial to maintain the reliability and sustainable service of large-scale data centers.
1 code implementation • 19 Apr 2021 • Hongzuo Xu, Yijie Wang, Songlei Jian, Zhenyu Huang, Ning Liu, Yongjun Wang, Fei Li
We obtain an optimal attention-guided embedding space with expanded high-level information and rich semantics, and thus outlying behaviors of the queried outlier can be better unfolded.
no code implementations • 13 Apr 2021 • Ning Liu, Songlei Jian, Dongsheng Li, Yiming Zhang, Zhiquan Lai, Hongzuo Xu
Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks.
1 code implementation • CVPR 2021 • Hongguang Zhang, Piotr Koniusz, Songlei Jian, Hongdong Li, Philip H. S. Torr
The majority of existing few-shot learning methods describe image relations with binary labels.
no code implementations • 8 Sep 2019 • Xugang Wu, XiaoPing Wang, Xu Zhou, Songlei Jian
On this basis, we formulate the adversarial generation problem and propose an end-to-end pipeline to generate a perturbed texture map for the 3D object that causes the trackers to fail.