no code implementations • 30 Oct 2024 • Jin Huang, Xinyu Li, Liang Gao, Qihao Liu, Yue Teng
To enhance the capabilities of LLMs in automatic HDRs design, this paper proposes a novel population self-evolutionary (SeEvo) method, a general search framework inspired by the self-reflective design strategies of human experts.
1 code implementation • 15 Jun 2023 • Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng, Liang Gao, Weiming Shen
This technical report introduces the winning solution of the team Segment Any Anomaly for the CVPR2023 Visual Anomaly and Novelty Detection (VAND) challenge.
2 code implementations • 18 May 2023 • Yunkang Cao, Xiaohao Xu, Chen Sun, Yuqi Cheng, Zongwei Du, Liang Gao, Weiming Shen
We present a novel framework, i. e., Segment Any Anomaly + (SAA+), for zero-shot anomaly segmentation with hybrid prompt regularization to improve the adaptability of modern foundation models.
Ranked #1 on
Anomaly Detection
on KSDD2
1 code implementation • 1 Sep 2022 • Chen Sun, Liang Gao, Xinyu Li, Yiping Gao
The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning.
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 #44 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 #17 on
Anomaly Detection
on MVTec AD
(Segmentation AUPRO metric)
1 code implementation • CVPR 2022 • Liang Gao, Huazhu Fu, Li Li, YingWen Chen, Ming Xu, Cheng-Zhong Xu
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data.
no code implementations • 7 Sep 2021 • Jin Xie, Xinyu Li, Liang Gao, Lin Gui
According to the above finding, this paper proposes a new N8 neighborhood structure considering the movement of critical operations within a critical block and the movement of critical operations outside the critical block.
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 #73 on
Anomaly Detection
on MVTec AD
(using extra training data)
3 code implementations • 31 May 2021 • Fuxiang Tan, YuTing Kong, Yingying Fan, Feng Liu, Daxin Zhou, Hao Zhang, Long Chen, Liang Gao, Yurong Qian
The former implements the basic rain pattern feature extraction, while the latter fuses different features to further extract and process the image features.
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 #97 on
Anomaly Detection
on MVTec AD
no code implementations • 13 Feb 2019 • Chen Sun, Ye Tian, Liang Gao, Yishuai Niu, Tianlong Zhang, Hua Li, Yuqing Zhang, Zengqi Yue, Nicole Delepine-Gilon, Jin Yu
Machine learning has been used to develop the model.
no code implementations • 29 Oct 2018 • Haozhen Dong, Liang Gao, Xinyu Li, Haoran Zhong, Bing Zeng
Differential evolution(DE) is a conventional algorithm with fast convergence speed.
no code implementations • 9 Apr 2018 • Bing Zeng, Xinyu Li, Liang Gao, Yuyan Zhang, Haozhen Dong
However, there are two difficulties urgently to be solved for most existing niching metaheuristic algorithms: how to set the optimal values of niching parameters for different optimization problems, and how to jump out of the local optima efficiently.
no code implementations • 24 May 2017 • Wei Cui, Liang Gao
We present an optical mapping near-eye (OMNI) three-dimensional display method for wearable devices.
no code implementations • 11 Feb 2017 • Bing Zeng, Liang Gao, Xinyu Li
Increasing nature-inspired metaheuristic algorithms are applied to solving the real-world optimization problems, as they have some advantages over the classical methods of numerical optimization.
5 code implementations • 5 Apr 2005 • Volker Springel, Simon D. M. White, Adrian Jenkins, Carlos S. Frenk, Naoki Yoshida, Liang Gao, Julio Navarro, Robert Thacker, Darren Croton, John Helly, John A. Peacock, Shaun Cole, Peter Thomas, Hugh Couchman, August Evrard, Joerg Colberg, Frazer Pearce
The cold dark matter model has become the leading theoretical paradigm for the formation of structure in the Universe.
astro-ph