no code implementations • 3 Feb 2025 • Sheng Fang, Yong-Jin Liu, Wei Yao, Chengming Yu, Jin Zhang
Bilevel optimization, addressing challenges in hierarchical learning tasks, has gained significant interest in machine learning.
no code implementations • 10 Dec 2024 • Fei Ma, Yukan Li, Yifan Xie, Ying He, Yi Zhang, Hongwei Ren, Zhou Liu, Wei Yao, Fuji Ren, Fei Richard Yu, Shiguang Ni
Specifically, this review will first present the review methodology, the emotion models involved, the mathematical principles of generative models, and the datasets used.
no code implementations • 24 Oct 2024 • A M Muntasir Rahman, Junyi Ye, Wei Yao, Wenpeng Yin, Guiling Wang
This discrepancy prompts a key question: Are current LLMs merely Blind Solver that apply mathematical operations without deeper reasoning, or can they function as Logical Thinker capable of identifying logical inconsistencies?
no code implementations • 9 Oct 2024 • Przemyslaw Polewski, Jacquelyn Shelton, Wei Yao, Marco Heurich
We formulate the problem as Bayesian maximum a posteriori inference which, in learning the individual object contours, incorporates shape, location, and position priors from state-of-the-art CNN architectures, driving a simultaneous level-set evolution of multiple object contours.
no code implementations • 9 Oct 2024 • Wei Yao, Zeliang Zhang, Huayi Tang, Yong liu
Model ensemble adversarial attack has become a powerful method for generating transferable adversarial examples that can target even unknown models, but its theoretical foundation remains underexplored.
no code implementations • 12 Sep 2024 • Weixiang Zhang, Shuzhao Xie, Shijia Ge, Wei Yao, Chen Tang, Zhi Wang
Neural Radiance Field (NeRF) has achieved remarkable success in creating immersive media representations through its exceptional reconstruction capabilities.
no code implementations • 8 Jul 2024 • Puzuo Wang, Wei Yao, Jie Shao, Zhiyi He
For photogrammetric (SensatUrban) to airborne (Hessigheim 3D) adaptation at the inference stage, our method achieves 59. 46\% mIoU and 85. 97\% OA without retraining or fine-turning.
no code implementations • 3 Jul 2024 • Li Fang, Tianyu Li, Yanghong Lin, Shudong Zhou, Wei Yao
Extensive experiments on the 3DRN benchmark dataset, featuring diverse urban environments with virtual TLS reflection noise, show our algorithm improves precision and recall rates for 3D points in reflective regions by 57. 03\% and 31. 80\%, respectively.
1 code implementation • 17 Jun 2024 • Wenkai Yang, Shiqi Shen, Guangyao Shen, Wei Yao, Yong liu, Zhi Gong, Yankai Lin, Ji-Rong Wen
However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know.
no code implementations • 29 May 2024 • Tianshu Chu, Dachuan Xu, Wei Yao, Jin Zhang
While stochastic bilevel optimization methods have been extensively studied for addressing large-scale nested optimization problems in machine learning, it remains an open question whether the optimal complexity bounds for solving bilevel optimization are the same as those in single-level optimization.
no code implementations • 16 May 2024 • Risheng Liu, Zhu Liu, Wei Yao, Shangzhi Zeng, Jin Zhang
This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures.
1 code implementation • 21 Apr 2024 • Jie Shao, Wei Yao, Lei Luo, Linzhou Zeng, Zhiyi He, Puzuo Wang, Huadong Guo
Greenspaces are tightly linked to human well-being.
no code implementations • 4 Mar 2024 • Zhiyi He, Wei Yao, Jie Shao, Puzuo Wang
Then, a new fine-grained classification network with Category Information Balancing Module (CIBM) and Contrastive Supervision (CS) technique is proposed to mitigate the problem of class imbalance and improve the classification robustness and accuracy.
1 code implementation • 29 Feb 2024 • Chen Qian, Jie Zhang, Wei Yao, Dongrui Liu, Zhenfei Yin, Yu Qiao, Yong liu, Jing Shao
This research provides an initial exploration of trustworthiness modeling during LLM pre-training, seeking to unveil new insights and spur further developments in the field.
no code implementations • 29 Jan 2024 • Wei Yao, Chengming Yu, Shangzhi Zeng, Jin Zhang
To address this challenge, we begin by devising a smooth proximal Lagrangian value function to handle the constrained lower-level problem.
no code implementations • 23 Jan 2024 • Guoxin Si, Shiliang Fu, Wei Yao
We have divided methane emission monitoring into three subtasks: methane concentration inversion, plume segmentation, and emission rate estimation.
no code implementations • 16 Jan 2024 • Zeliang Zhang, Wei Yao, Xiaosen Wang
In this work, we find that several tiny changes in the existing adversarial attacks can significantly affect the attack performance, \eg, the number of iterations and step size.
1 code implementation • 3 Jan 2024 • Wei Yao, Hongwen Zhang, Yunlian Sun, Jinhui Tang
This method can remarkably improve the smoothness of recovery results from video.
Ranked #51 on
3D Human Pose Estimation
on MPI-INF-3DHP
(using extra training data)
no code implementations • 5 Dec 2023 • Xu Shi, Wei Yao, Chuanchen Luo, Junran Peng, Hongwen Zhang, Yunlian Sun
By adopting a divide-and-conquer strategy, we propose a new framework named Fine-Grained Human Motion Diffusion Model (FG-MDM) for zero-shot human motion generation.
1 code implementation • 29 Nov 2023 • Wei Yao, Hongwen Zhang, Yunlian Sun, Yebin Liu, Jinhui Tang
Our contributions include a novel weak-supervised camera calibration technique, an effective orientation correction module, and a decoupling strategy that significantly improves the generalizability and accuracy of human motion recovery in both camera and world coordinates.
Ranked #1 on
3D Human Pose Estimation
on SPEC-MTP
(using extra training data)
1 code implementation • 17 Oct 2023 • Wei Yao, Zhanke Zhou, Zhicong Li, Bo Han, Yong liu
To mitigate such bias while achieving comparable accuracy, a promising approach is to introduce surrogate functions of the concerned fairness definition and solve a constrained optimization problem.
no code implementations • 20 Jun 2023 • Shaocheng Jia, Wei Yao
Extensive experiments on the synthesized data from the KITTI and real-world data collected in Beijing demonstrate that the proposed method can (1) achieve performance competitive in depth estimation as compared with state-of-the-art methods when taking clear images as input; (2) predict vivid depth map for images contaminated by various levels of haze; and (3) accurately estimate visibility, airlight, and PM2. 5 mass concentrations.
no code implementations • 23 Apr 2023 • Jie Shao, Wei Yao, Puzuo Wang, Zhiyi He, Lei Luo
In this paper, we propose a complementary strategy that integrates LiDAR point clouds with as-designed BIM models for reconstructing urban scenes.
1 code implementation • 7 Feb 2023 • Risheng Liu, Yaohua Liu, Wei Yao, Shangzhi Zeng, Jin Zhang
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning fields.
no code implementations • 4 Jan 2023 • Tsz Chung Wong, Abubakar Sani-Mohammed, Jinhong Wang, Puzuo Wang, Wei Yao, Marco Heurich
Finally, the classification is conducted on the two datasets (3D multispectral point clouds and 2D projected images) based on the three Machine Learning algorithms.
1 code implementation • CVPR 2023 • Pengwei Tang, Wei Yao, Zhicong Li, Yong liu
We randomly initialize a dense neural network and find appropriate binary masks for the weights to obtain fair sparse subnetworks without any weight training.
no code implementations • 9 Dec 2022 • Mingze Sun, Haoxiang Wang, Wei Yao, Jiawang Liu
Recent studies have found that pain in infancy has a significant impact on infant development, including psychological problems, possible brain injury, and pain sensitivity in adulthood.
no code implementations • 23 Nov 2022 • Puzuo Wang, Wei Yao, Jie Shao
It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes.
no code implementations • 20 Oct 2022 • Yi Liu, Xuan Zhang, Ying Li, Guixin Liang, Yabing Jiang, Lixia Qiu, Haiping Tang, Fei Xie, Wei Yao, Yi Dai, Yu Qiao, Yali Wang
For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis.
no code implementations • 20 May 2022 • Risheng Liu, Xuan Liu, Wei Yao, Shangzhi Zeng, Jin Zhang
Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in learning and vision fields.
no code implementations • 14 Apr 2022 • Rong Huang, Wei Yao, Zhong Xu, Lin Cao, Xin Shen
The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve using a system that synergistically combines an unmanned aircraft system (UAS)-based digital aerial camera and LiDAR to leverage their complementary advantages.
no code implementations • 18 Feb 2022 • Shaocheng Jia, Wei Yao
Current artificial neural networks mainly conduct the learning process in the spatial domain but neglect the frequency domain learning.
no code implementations • 27 Jan 2022 • Jie Shao, Wei Yao, Peng Wan, Lei Luo, Jiaxin Lyu, Wuming Zhang
Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration.
no code implementations • 6 Dec 2021 • Jacquelyn A. Shelton, Przemyslaw Polewski, Wei Yao, Marco Heurich
This improved performance is essential to meet emerging challenges caused by climate change (and other man-made perturbations to the systems), particularly to monitor and estimate carbon stock decay rates, monitor forest health and biodiversity, and the overall effects of dead wood on and from climate change.
no code implementations • 4 Oct 2021 • Puzuo Wang, Wei Yao
For the ISPRS 3D Labeling Vaihingen data, by using only 0. 1% of labels, our method achieves an overall accuracy of 83. 0% and an average F1 score of 70. 0%, which have increased by 6. 9% and 12. 8% respectively, compared to model trained by sparse label information only.
no code implementations • 27 Jul 2021 • Hang Shuai, Xiaomeng Ai, Jiakun Fang, Wei Yao, Senior Member, Jinyu Wen, Member, IEEE
It is challenging to solve this kind of stochastic nonlinear optimization problem.
no code implementations • 7 Jun 2021 • Shaocheng Jia, Xin Pei, Wei Yao, S. C. Wong
Self-supervised depth estimation has drawn much attention in recent years as it does not require labeled data but image sequences.
no code implementations • 6 May 2021 • Jacquelyn Shelton, Przemyslaw Polewski, Wei Yao
Since the outbreak of COVID-19 policy makers have been relying upon non-pharmacological interventions to control the outbreak.
no code implementations • 5 May 2021 • Puzuo Wang, Wei Yao
Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data.
no code implementations • 5 May 2021 • Przemyslaw Polewski, Jacquelyn Shelton, Wei Yao, Marco Heurich
In this paper, we introduce a framework for segmenting instances of a common object class by multiple active contour evolution over semantic segmentation maps of images obtained through fully convolutional networks.
no code implementations • 5 May 2021 • Rong Huang, Wei Yao, Yusheng Xu, Zhen Ye, Uwe Stilla
Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds.
no code implementations • 31 Dec 2020 • Shen Chen, Mingwei Zhang, Jiamin Cui, Wei Yao
In this paper, we intend to address this problem by presenting a generalized operating procedure for DL from the perspective of unconstrained optimal design, which is motivated by a simple intension to remove the barrier of using DL, especially for those scientists or engineers who are new but eager to use it.
no code implementations • 21 Dec 2020 • Wei Yao, Shen Chen, Jiamin Cui, Yaolin Lou
For the diversity of temporal embeddings, we consider feature augmentation with frequency selection, which is to manually segment the full-band of frequency into several sub-bands, and the feature extractor of each stream can select which sub-bands to use as target frequency domain.
no code implementations • 1 Apr 2019 • Jinguang Sun, Wanli Wang, Xian Wei, Li Fang, Xiaoliang Tang, Yusheng Xu, Hui Yu, Wei Yao
The high dimensionality of hyperspectral images often results in the degradation of clustering performance.
no code implementations • 23 Mar 2019 • Hai-Tao Zhang, Lingguo Meng, Xian Wei, Xiaoliang Tang, Xuan Tang, Xingping Wang, Bo Jin, Wei Yao
The complex structure of CNNs results in prohibitive training efforts.
1 code implementation • 6 Nov 2017 • Dimitrios Marmanis, Wei Yao, Fathalrahman Adam, Mihai Datcu, Peter Reinartz, Konrad Schindler, Jan Dirk Wegner, Uwe Stilla
Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field.