1 code implementation • 16 Jan 2025 • Hanrong Zhang, Yifei Yao, Zixuan Wang, Jiayuan Su, Mengxuan Li, Peng Peng, Hongwei Wang
Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge.
no code implementations • 27 Jun 2023 • Xingyue Wang, Hanrong Zhang, Xinlong Qiao, Ke Ma, Shuting Tao, Peng Peng, Hongwei Wang
Additionally, a unified fault diagnosis method based on internal contrastive learning and Mahalanobis distance is put forward to underpin the proposed generalized framework.
no code implementations • 26 Jun 2023 • Zixuan Wang, Bo Qin, Mengxuan Li, Chenlu Zhan, Mark D. Butala, Peng Peng, Hongwei Wang
The proposed method employs cosine similarity to identify hard samples and subsequently, leverages supervised contrastive learning to learn more discriminative representations by constructing hard sample pairs.
no code implementations • 13 Feb 2023 • Mengxuan Li, Peng Peng, Min Wang, Hongwei Wang
The novelty of HDLCNN lies in its capability of processing tabular data with features of arbitrary order without seeking the optimal order, due to the ability to agglomerate correlated features of feature clustering and the large receptive field of dilated convolution.
no code implementations • 12 Feb 2023 • Peng Peng, Hanrong Zhang, Mengxuan Li, Gongzhuang Peng, Hongwei Wang, Weiming Shen
Finally, the model decision is biased toward the new classes due to the class imbalance.
no code implementations • 3 Feb 2023 • Mengxuan Li, Peng Peng, Jingxin Zhang, Hongwei Wang, Weiming Shen
The comprehensive results demonstrate that the proposed SCCAM method can achieve better performance compared with the state-of-the-art methods on fault classification and root cause analysis.
no code implementations • 21 Dec 2022 • Chenlu Zhan, Peng Peng, Hongsen Wang, Tao Chen, Hongwei Wang
Moreover, for grasping the unified semantic representation, we extend the adversarial masking data augmentation to the contrastive representation learning of vision and text in a unified manner.
no code implementations • 19 Oct 2022 • Shuting Tao, Peng Peng, Qi Li, Hongwei Wang
To solve this problem, we propose a Supervised Contrastive Learning (SCL) method with Tree-structured Parzen Estimator (TPE) technique for imbalanced tabular datasets.
no code implementations • 22 Jun 2022 • Xinyu Zhang, Peng Peng, Yushan Zhou, Haifeng Wang, Wenxin Li
First, there is inaccuracy when analysing the simplified payoff table.
no code implementations • 22 Nov 2021 • Yijun Cao, Xianshi Zhang, Fuya Luo, Peng Peng, YongJie Li
The experiments show that the proposed system not only achieves comparable performance with other state-of-the-art self-supervised learning-based methods on the KITTI dataset, but also significantly improves the generalization capability compared with geometry-based, learning-based and hybrid VO systems on the noisy KITTI and the challenging outdoor (KAIST) scenes.
1 code implementation • 29 Apr 2021 • Fuya Luo, Yunhan Li, Guang Zeng, Peng Peng, Gang Wang, YongJie Li
Furthermore, a new metric is devised to evaluate the geometric consistency in the translation process.
no code implementations • 24 Dec 2020 • Xiangjun Wang, Junxiao Song, Penghui Qi, Peng Peng, Zhenkun Tang, Wei zhang, Weimin Li, Xiongjun Pi, Jujie He, Chao GAO, Haitao Long, Quan Yuan
In this paper, we will share the key insights and optimizations on efficient imitation learning and reinforcement learning for StarCraft II full game.
no code implementations • 1 Dec 2020 • Peng Peng, Jiugen Wang
Fine-tuning of a deep model is simple and effective few-shot learning method.
no code implementations • 1 Dec 2020 • Peng Peng, Yong-Jie Li
The proposed structure is simple yet effective; the rich context information of RGB and depth can be appropriately extracted and fused by the proposed structure efficiently.
no code implementations • 20 Nov 2020 • Peng Peng, Jiugen Wang
The region segmentation network is an improved U shape network, and it is applied to separate the wear debris form background of ferrograph image.
no code implementations • 14 Oct 2020 • Peng Peng, Jiugen Wang
For the problem of insufficient samples, we first proposed a data augmentation algorithm based on the permutation of image patches.
1 code implementation • 7 Feb 2019 • Łukasz Kidziński, Carmichael Ong, Sharada Prasanna Mohanty, Jennifer Hicks, Sean F. Carroll, Bo Zhou, Hongsheng Zeng, Fan Wang, Rongzhong Lian, Hao Tian, Wojciech Jaśkowski, Garrett Andersen, Odd Rune Lykkebø, Nihat Engin Toklu, Pranav Shyam, Rupesh Kumar Srivastava, Sergey Kolesnikov, Oleksii Hrinchuk, Anton Pechenko, Mattias Ljungström, Zhen Wang, Xu Hu, Zehong Hu, Minghui Qiu, Jun Huang, Aleksei Shpilman, Ivan Sosin, Oleg Svidchenko, Aleksandra Malysheva, Daniel Kudenko, Lance Rane, Aditya Bhatt, Zhengfei Wang, Penghui Qi, Zeyang Yu, Peng Peng, Quan Yuan, Wenxin Li, Yunsheng Tian, Ruihan Yang, Pingchuan Ma, Shauharda Khadka, Somdeb Majumdar, Zach Dwiel, Yinyin Liu, Evren Tumer, Jeremy Watson, Marcel Salathé, Sergey Levine, Scott Delp
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector.
no code implementations • 18 Dec 2018 • Peng Peng, Liang Pang, Yufeng Yuan, Chao GAO
We show in the experiments that Pommerman is a perfect environment for studying continual learning, and the agent can improve its performance by continually learning new skills without forgetting the old ones.
2 code implementations • 29 Mar 2017 • Peng Peng, Ying Wen, Yaodong Yang, Quan Yuan, Zhenkun Tang, Haitao Long, Jun Wang
Many artificial intelligence (AI) applications often require multiple intelligent agents to work in a collaborative effort.