no code implementations • 30 Mar 2024 • Qian Wan, Xiang Xiang, Qinhao Zhou
Because of its use in practice, open-world object detection (OWOD) has gotten a lot of attention recently.
no code implementations • 1 Mar 2024 • Qian Wan, Xin Feng, Yining Bei, Zhiqi Gao, Zhicong Lu
It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness.
no code implementations • 20 Jul 2023 • Qian Wan, Siying Hu, Yu Zhang, Piaohong Wang, Bo Wen, Zhicong Lu
This collaborative process champions the human in a dominant role, in addition to mixed and shifting levels of initiative that exist between humans and LLMs.
no code implementations • ICCV 2023 • ShouWen Wang, Qian Wan, Xiang Xiang, Zhigang Zeng
In this paper, we propose saliency regularization (SR) for a novel self-training framework.
1 code implementation • Knowledge-Based Systems 2022 • Yunkang Cao, Qian Wan, Weiming Shen, Liang Gao
However, rare attention has been paid to the overfitting problem caused by the inconsistency between the capacity of the neural network and the amount of knowledge in this scheme.
Ranked #27 on Anomaly Detection on MVTec AD (Segmentation AUPRO metric)
1 code implementation • 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE) 2022 • Qian Wan, Yunkang Cao, Liang Gao, Weiming Shen, Xinyu Li
Image anomaly detection is an important stage for automatic visual inspection in intelligent manufacturing systems.
Ranked #11 on Anomaly Detection on MVTec AD (Segmentation AUPRO metric)
1 code implementation • 24 Nov 2021 • Xiang Xiang, Yuwen Tan, Qian Wan, Jing Ma
Such images form a new training set (i. e., support set) so that the incremental model is hoped to recognize a basenji (i. e., query) as a basenji next time.
1 code implementation • IEEE Transactions on Industrial Informatics 2021 • Qian Wan, Liang Gao, Xinyu Li, long wen
This paper proposes a novel framework, named as Pre-trained Feature Mapping (PFM), for unsupervised image anomaly detection and segmentation.
Ranked #51 on Anomaly Detection on MVTec AD
1 code implementation • IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2021 • Qian Wan, Liang Gao, Xinyu Li, long wen
Anomaly localization is valuable for improvement of complex production processing in smart manufacturing system.
Ranked #70 on Anomaly Detection on MVTec AD
no code implementations • 7 Oct 2019 • Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox
Teleoperation offers the possibility of imparting robotic systems with sophisticated reasoning skills, intuition, and creativity to perform tasks.
no code implementations • 10 Oct 2016 • Qian Wan, Huiping Duan, Jun Fang, Hongbin Li
We consider the problem of robust compressed sensing whose objective is to recover a high-dimensional sparse signal from compressed measurements corrupted by outliers.