no code implementations • 23 Apr 2024 • Yingqing Guo, Hui Yuan, Yukang Yang, Minshuo Chen, Mengdi Wang
To remedy this issue, we consider a modified form of gradient guidance based on a forward prediction loss, which leverages the pre-trained score function to preserve the latent structure in generated samples.
1 code implementation • 22 Apr 2024 • Kamyar Barakati, Hui Yuan, Amit Goyal, Sergei V. Kalinin
We present a methodology based on the concept of a Reward Function coupled with Bayesian Optimization, to optimize image analysis workflows dynamically.
no code implementations • 20 Mar 2024 • Zihao Li, Hui Yuan, Kaixuan Huang, Chengzhuo Ni, Yinyu Ye, Minshuo Chen, Mengdi Wang
In this paper, we focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization over complex structured variables.
no code implementations • 14 Feb 2024 • Souradip Chakraborty, Jiahao Qiu, Hui Yuan, Alec Koppel, Furong Huang, Dinesh Manocha, Amrit Singh Bedi, Mengdi Wang
Reinforcement Learning from Human Feedback (RLHF) aligns language models to human preferences by employing a singular reward model derived from preference data.
no code implementations • 8 Jan 2024 • Jiahao Qiu, Hui Yuan, Jinghong Zhang, Wentao Chen, Huazheng Wang, Mengdi Wang
To enhance the efficiency of such a process, we propose a tree search-based bandit learning method, which expands a tree starting from the initial sequence with the guidance of a bandit machine learning model.
1 code implementation • NeurIPS 2023 • Jinhui Hou, Zhiyu Zhu, Junhui Hou, Hui Liu, Huanqiang Zeng, Hui Yuan
To harness the capabilities of diffusion models, we delve into this intricate process and advocate for the regularization of its inherent ODE-trajectory.
Ranked #2 on Low-Light Image Enhancement on LOL
no code implementations • 21 Sep 2023 • Yanbo Gao, Wenjia Huang, Shuai Li, Hui Yuan, Mao Ye, Siwei Ma
Similar as the traditional video coding, LVC inherits motion estimation/compensation, residual coding and other modules, all of which are implemented with neural networks (NNs).
2 code implementations • NeurIPS 2023 • Zeyu Zhang, Yi Su, Hui Yuan, Yiran Wu, Rishab Balasubramanian, Qingyun Wu, Huazheng Wang, Mengdi Wang
Building upon this, we leverage offline RL techniques for off-policy LTR and propose the Click Model-Agnostic Unified Off-policy Learning to Rank (CUOLR) method, which could be easily applied to a wide range of click models.
no code implementations • 30 May 2023 • Zichen Wang, Rishab Balasubramanian, Hui Yuan, Chenyu Song, Mengdi Wang, Huazheng Wang
We propose the first study of adversarial attacks on online learning to rank.
1 code implementation • 27 Apr 2023 • Zihao Li, Pan Gao, Hui Yuan, Ran Wei, Manoranjan Paul
Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
Ranked #1 on 3D Object Classification on ModelNet40
1 code implementation • 24 Mar 2023 • Jinrui Xing, Hui Yuan, Raouf Hamzaoui, Hao liu, Junhui Hou
To reduce color distortion in point clouds, we propose a graph-based quality enhancement network (GQE-Net) that uses geometry information as an auxiliary input and graph convolution blocks to extract local features efficiently.
1 code implementation • 7 Jan 2023 • Zihao Li, Pan Gao, Hui Yuan, Ran Wei
Existing point cloud learning methods aggregate features from neighbouring points relying on constructing graph in the spatial domain, which results in feature update for each point based on spatially-fixed neighbours throughout layers.
no code implementations • 30 Nov 2022 • Qi Liu, Yiyun Liu, Honglei Su, Hui Yuan, Raouf Hamzaoui
In this paper, a progressive knowledge transfer based on human visual perception mechanism for perceptual quality assessment of point clouds (PKT-PCQA) is proposed.
no code implementations • 5 Jun 2022 • Hui Yuan, Chengzhuo Ni, Huazheng Wang, Xuezhou Zhang, Le Cong, Csaba Szepesvári, Mengdi Wang
We propose a Thompson Sampling-guided Directed Evolution (TS-DE) framework for sequence optimization, where the sequence-to-function mapping is unknown and querying a single value is subject to costly and noisy measurements.
no code implementations • 2 Mar 2022 • Hao liu, Hui Yuan, Junhui Hou, Raouf Hamzaoui, Wei Gao
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions.
1 code implementation • 3 Nov 2021 • Yuqi Nie, Hui Yuan
We find a heterogeneity in both complex and real valued neural networks with the insight from wave optics, claiming a much more important role of phase than its amplitude counterpart in the weight matrix.
no code implementations • 24 Jun 2021 • Jian Yue, Yanbo Gao, Shuai Li, Hui Yuan, Frédéric Dufaux
To the best of our knowledge, we are the first one that clearly characterizes the video filtering process from the above global appearance and local coding distortion restoration aspects with experimental verification, providing a clear pathway to developing filter techniques.
no code implementations • 5 Apr 2021 • Huisheng Gao, Hui Yuan, Huanhai Xin, Linbin Huang, Chaoyou Feng
Then, we present how the initial RoCoF of the nodal frequencies are related to the inertia constants of multiple generators in a power network, which leads to a performance metric to analyze nodal frequency performance.
no code implementations • 1 Jan 2021 • Xin Ma, Zhicheng Zhang, Danfeng Wang, Yu Luo, Hui Yuan
In deep learning-based local stereo matching methods, larger image patches usually bring better stereo matching accuracy.
1 code implementation • CVPR 2021 • Yiming Zeng, Yue Qian, Zhiyu Zhu, Junhui Hou, Hui Yuan, Ying He
The symmetric deformer, with an additional regularized loss, transforms the two permuted point clouds to each other to drive the unsupervised learning of the correspondence.
Ranked #6 on 3D Dense Shape Correspondence on SHREC'19 (using extra training data)
no code implementations • 25 Nov 2020 • Qi Liu, Hui Yuan, Raouf Hamzaoui, Honglei Su, Junhui Hou, Huan Yang
In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate.
no code implementations • 31 Aug 2020 • Alessandro Ottino, Hui Yuan, Yunnuo Xu, Eric Sillekens, Georgios Zervas
In addition, this model is consistent with statistical analysis such as short term average crosstalk (STAXT), keeping the same convergence properties and it showed to be almost independent to time-window.
no code implementations • 7 Aug 2020 • Hui Yuan, Alessandro Ottino, Yunnuo Xu, Arsalan Saljoghei, Tetsuya Hayashi, Tetsuya Nakanishi, Eric Sillekens, Lidia Galdino, Polina Bayvel, Zhixin Liu, Georgios Zervas
Space division multiplexing using multi-core fiber (MCF) is a promising solution to cope with the capacity crunch in standard single-mode fiber based optical communication systems.
no code implementations • 10 Jul 2020 • Yingyu Liang, Hui Yuan
In the setting of entangled single-sample distributions, the goal is to estimate some common parameter shared by a family of $n$ distributions, given one single sample from each distribution.
no code implementations • 20 Apr 2020 • Hui Yuan, YIngyu Liang
We study mean estimation and linear regression under general conditions, and analyze a simple and computationally efficient method based on iteratively trimming samples and re-estimating the parameter on the trimmed sample set.
1 code implementation • 26 Feb 2020 • Jing Jin, Junhui Hou, Hui Yuan, Sam Kwong
In addition, our method preserves the light field parallax structure better.
no code implementations • 27 Dec 2019 • Hui Yuan, Huayong Fu, Ju Liu, Junhui Hou, Sam Kwong
The proposed algorithm is proxy-free.
no code implementations • 26 Dec 2019 • Hui Yuan, Xiaoqian Hu, Junhui Hou, Xuekai Wei, Sam Kwong
Specifically, the proposed framework is composed of two modules, i. e., the method pool and method controller.
no code implementations • 20 Dec 2019 • Hao Liu, Hui Yuan, Qi Liu, Junhui Hou, Ju Liu
Point cloud based 3D visual representation is becoming popular due to its ability to exhibit the real world in a more comprehensive and immersive way.
no code implementations • 20 Dec 2019 • Hui Yuan, Shiyun Zhao, Junhui Hou, Xuekai Wei, Sam Kwong
That is, our method preserves both the quality and the smoothness of tiles in FoV, thus providing the best QoE for users.
no code implementations • 22 Jul 2019 • Hui Yuan, Mengyu Li, Junhui Hou, Jimin Xiao
Specifically, the rectangular coordinates of only four non-coplanar feature points from a predefined 3D facial model as well as the corresponding ones automatically/ manually extracted from a 2D face image are first normalized to exclude the effect of external factors (i. e., scale factor and translation parameters).
no code implementations • 23 Jan 2019 • Jonathan Schwartz, Yi Jiang, Yongjie Wang, Anthony Aiello, Pallab Bhattacharya, Hui Yuan, Zetian Mi, Nabil Bassim, Robert Hovden
Highly-directional image artifacts such as ion mill curtaining, mechanical scratches, or image striping from beam instability degrade the interpretability of micrographs.