1 code implementation • EMNLP 2023 • Jize Wang, Xinyi Le, Xiaodi Peng, Cailian Chen
In this paper, we propose to downweight the easy negatives by utilizing a distance between the classification threshold and the predicted score of each relation.
Ranked #2 on Relation Extraction on ReDocRED
Document-level Relation Extraction Multi-Label Classification +1
no code implementations • 5 Sep 2022 • Zhiyuan You, Kai Yang, Wenhan Luo, Lei Cui, Yu Zheng, Xinyi Le
Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish.
1 code implementation • 8 Jun 2022 • Zhiyuan You, Lei Cui, Yujun Shen, Kai Yang, Xin Lu, Yu Zheng, Xinyi Le
For example, when learning a unified model for 15 categories in MVTec-AD, we surpass the second competitor on the tasks of both anomaly detection (from 88. 1% to 96. 5%) and anomaly localization (from 89. 5% to 96. 8%).
no code implementations • 17 Apr 2022 • Bao Zhao, Xianyong Fang, Jiahui Yue, Xiaobo Chen, Xinyi Le, Chanjuan Zhao
The performance of these methods are comprehensively evaluated on six standard datasets with different application scenarios and nuisances.
1 code implementation • CVPR 2022 • Yuchao Wang, Haochen Wang, Yujun Shen, Jingjing Fei, Wei Li, Guoqiang Jin, Liwei Wu, Rui Zhao, Xinyi Le
A common practice is to select the highly confident predictions as the pseudo ground-truth, but it leads to a problem that most pixels may be left unused due to their unreliability.
1 code implementation • 22 Jan 2022 • Zhiyuan You, Kai Yang, Wenhan Luo, Xin Lu, Lei Cui, Xinyi Le
This work studies the problem of few-shot object counting, which counts the number of exemplar objects (i. e., described by one or several support images) occurring in the query image.
Ranked #2 on Object Counting on CARPK
2 code implementations • CVPR 2020 • Zitian Huang, Yikuan Yu, Jiawen Xu, Feng Ni, Xinyi Le
Unlike existing point cloud completion networks, which generate the overall shape of the point cloud from the incomplete point cloud and always change existing points and encounter noise and geometrical loss, PF-Net preserves the spatial arrangements of the incomplete point cloud and can figure out the detailed geometrical structure of the missing region(s) in the prediction.
no code implementations • 16 Jan 2019 • Bao Zhao, Xiaobo Chen, Xinyi Le, Juntong Xi
This paper evaluates eleven state-of-the-art transformation estimation proposals on both descriptor based and synthetic correspondences.
no code implementations • 15 Nov 2017 • Bao Zhao, Xinyi Le, Juntong Xi
Besides, an improved LRA is proposed for increasing the robustness of our SDASS to noise and varying mesh resolutions.