no code implementations • 11 Mar 2024 • Zhi Cao, Youneng Bao, Fanyang Meng, Chao Li, Wen Tan, Genhong Wang, Yongsheng Liang
Adversarial training has been validated in image compression models as a common method to enhance model robustness.
no code implementations • 6 Sep 2023 • Shanzhi Yin, Tongda Xu, Yongsheng Liang, Yuanyuan Wang, Yanghao Li, Yan Wang, Jingjing Liu
With neural networks growing deeper and feature maps growing larger, limited communication bandwidth with external memory (or DRAM) and power constraints become a bottleneck in implementing network inference on mobile and edge devices.
no code implementations • 23 Jun 2022 • Bowen Li, Yao Xin, Youneng Bao, Fanyang Meng, Yongsheng Liang, Wen Tan
Recently, learned image compression methods have developed rapidly and exhibited excellent rate-distortion performance when compared to traditional standards, such as JPEG, JPEG2000 and BPG.
no code implementations • 4 Apr 2022 • Qiuhong Shen, Xin Li, Fanyang Meng, Yongsheng Liang
These deep trackers usually do not perform online update or update single sub-branch of the tracking model, for which they cannot adapt to the appearance variation of objects.
no code implementations • 4 Mar 2022 • Youneng Bao, Fangyang Meng, Wen Tan, Chao Li, Yonghong Tian, Yongsheng Liang
In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation.
no code implementations • 9 Feb 2022 • Shanzhi Yin, Chao Li, Wen Tan, Youneng Bao, Yongsheng Liang, Wei Liu
Neural image compression have reached or out-performed traditional methods (such as JPEG, BPG, WebP).
no code implementations • 18 Nov 2021 • Shanzhi Yin, Chao Li, Youneng Bao, Yongsheng Liang
Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP).
no code implementations • 3 Mar 2021 • Yongsheng Liang, Zhigang Ren, Lin Wang, Hanqing Liu, Wenhao Du
The decomposition operation significantly narrows the search space of the whole traffic network, and the surrogate-assisted optimizer greatly lowers the computational burden by reducing the number of expensive traffic simulations.
no code implementations • 1 Mar 2021 • Xiaodong Ren, Daofu Guo, Zhigang Ren, Yongsheng Liang, An Chen
By remarkably reducing real fitness evaluations, surrogate-assisted evolutionary algorithms (SAEAs), especially hierarchical SAEAs, have been shown to be effective in solving computationally expensive optimization problems.
no code implementations • 19 Jan 2021 • An Chen, Zhigang Ren, Muyi Wang, Yongsheng Liang, Hanqing Liu, Wenhao Du
SVG first designs a general-separability-oriented detection criterion according to whether the optimum of a variable changes with other variables.
no code implementations • 5 Jun 2020 • Honghu Pan, Fanyang Meng, Zhenyu He, Yongsheng Liang, Wei Liu
Then we define topology distance between descriptors as the difference of their topology vectors.
no code implementations • 5 Apr 2020 • Zhigang Ren, Yongsheng Liang, Muyi Wang, Yang Yang, An Chen
Different from existing DC-based algorithms that perform decomposition and optimization in the original decision space, EDC first establishes an eigenspace by conducting singular value decomposition on a set of high-quality solutions selected from recent generations.
no code implementations • 1 Mar 2018 • Bei Pang, Zhigang Ren, Yongsheng Liang, An Chen
As for the nonseparable sub-problems, the surrogate models are employed to evaluate the corresponding sub-solutions, and the original simulation model is only adopted to reevaluate some good sub-solutions selected by surrogate models.
no code implementations • 1 Mar 2018 • Yongsheng Liang, Zhigang Ren, Bei Pang, An Chen
As a model-based evolutionary algorithm, estimation of distribution algorithm (EDA) possesses unique characteristics and has been widely applied to global optimization.
no code implementations • 1 Mar 2018 • An Chen, Yi-Peng Zhang, Zhigang Ren, Yongsheng Liang, Bei Pang
On the one hand, by reducing the sensitivity of the indicator in DG to the roundoff error and the magnitude of contribution weight of subcomponent, we proposed a new indicator for two variables which is much more sensitive to their interaction.
no code implementations • 27 Feb 2018 • Zhigang Ren, Bei Pang, Yongsheng Liang, An Chen, Yi-Peng Zhang
It has been shown that cooperative coevolution (CC) can effectively deal with large scale optimization problems (LSOPs) through a divide-and-conquer strategy.
no code implementations • 27 Feb 2018 • Zhigang Ren, Yongsheng Liang, Aimin Zhang, Yang Yang, Zuren Feng, Lin Wang
Cooperative coevolution (CC) has shown great potential in solving large scale optimization problems (LSOPs).
no code implementations • 25 Feb 2018 • Yongsheng Liang, Zhigang Ren, Xianghua Yao, Zuren Feng, An Chen
This study first systematically analyses the reasons for the deficiency of the traditional GEDA, then tries to enhance its performance by exploiting its evolution direction, and finally develops a new GEDA variant named EDA2.
no code implementations • 22 Dec 2017 • Fanyang Meng, Hong Liu, Yongsheng Liang, Wei Liu, Jihong Pei
The bandwidth of a kernel function is a crucial parameter in the mean shift algorithm.