Search Results for author: Chenyang Wang

Found 21 papers, 12 papers with code

Estimating the Number of Components in Finite Mixture Models via Variational Approximation

no code implementations25 Apr 2024 Chenyang Wang, Yun Yang

This work introduces a new method for selecting the number of components in finite mixture models (FMMs) using variational Bayes, inspired by the large-sample properties of the Evidence Lower Bound (ELBO) derived from mean-field (MF) variational approximation.

Model Selection

Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning

no code implementations12 Jan 2024 Chenyang Wang, Junjun Jiang, Xingyu Hu, Xianming Liu, Xiangyang Ji

Using the measurement, we analyze existing techniques for inverting samples and get some insightful information that inspires a novel loss function to reduce the inconsistency.

Class Incremental Learning Incremental Learning

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring

no code implementations CVPR 2024 Xiaoqian Lv, Shengping Zhang, Chenyang Wang, Yichen Zheng, Bineng Zhong, Chongyi Li, Liqiang Nie

Existing joint low-light enhancement and deblurring methods learn pixel-wise mappings from paired synthetic data which results in limited generalization in real-world scenes.

Deblurring

Adaptive Stochastic Nonlinear Model Predictive Control with Look-ahead Deep Reinforcement Learning for Autonomous Vehicle Motion Control

no code implementations7 Nov 2023 Baha Zarrouki, Chenyang Wang, Johannes Betz

In this paper, we present a Deep Reinforcement Learning (RL)-driven Adaptive Stochastic Nonlinear Model Predictive Control (SNMPC) to optimize uncertainty handling, constraints robustification, feasibility, and closed-loop performance.

Decision Making Model Predictive Control +1

A Stochastic Nonlinear Model Predictive Control with an Uncertainty Propagation Horizon for Autonomous Vehicle Motion Control

no code implementations28 Oct 2023 Baha Zarrouki, Chenyang Wang, Johannes Betz

Our SNMPC approach utilizes Polynomial Chaos Expansion (PCE) to propagate uncertainties and incorporates nonlinear hard constraints on state expectations and nonlinear probabilistic constraints.

Autonomous Vehicles Model Predictive Control

Discrete Conditional Diffusion for Reranking in Recommendation

no code implementations14 Aug 2023 Xiao Lin, Xiaokai Chen, Chenyang Wang, Hantao Shu, Linfeng Song, Biao Li, Peng Jiang

To overcome these challenges, we propose a novel Discrete Conditional Diffusion Reranking (DCDR) framework for recommendation.

Recommendation Systems

Super-Resolving Face Image by Facial Parsing Information

1 code implementation6 Apr 2023 Chenyang Wang, Junjun Jiang, Zhiwei Zhong, Deming Zhai, Xianming Liu

In this paper, we build a novel parsing map guided face super-resolution network which extracts the face prior (i. e., parsing map) directly from low-resolution face image for the following utilization.

Super-Resolution

Modeling Sequential Recommendation as Missing Information Imputation

1 code implementation4 Jan 2023 Yujie Lin, Zhumin Chen, Zhaochun Ren, Chenyang Wang, Qiang Yan, Maarten de Rijke, Xiuzhen Cheng, Pengjie Ren

To address the limitation of sequential recommenders with side information, we define a way to fuse side information and alleviate the problem of missing side information by proposing a unified task, namely the missing information imputation (MII), which randomly masks some feature fields in a given sequence of items, including item IDs, and then forces a predictive model to recover them.

Imputation Sequential Recommendation

Spatial-Frequency Mutual Learning for Face Super-Resolution

1 code implementation CVPR 2023 Chenyang Wang, Junjun Jiang, Zhiwei Zhong, Xianming Liu

To circumvent this problem, Fourier transform is introduced, which can capture global facial structure information and achieve image-size receptive field.

Super-Resolution

Towards Representation Alignment and Uniformity in Collaborative Filtering

2 code implementations26 Jun 2022 Chenyang Wang, Yuanqing Yu, Weizhi Ma, Min Zhang, Chong Chen, Yiqun Liu, Shaoping Ma

Then, we empirically analyze the learning dynamics of typical CF methods in terms of quantified alignment and uniformity, which shows that better alignment or uniformity both contribute to higher recommendation performance.

Collaborative Filtering Graph Neural Network +1

From Less to More: Spectral Splitting and Aggregation Network for Hyperspectral Face Super-Resolution

no code implementations31 Aug 2021 Junjun Jiang, Chenyang Wang, Xianming Liu, Kui Jiang, Jiayi Ma

By this spectral splitting and aggregation strategy (SSAS), we can divide the original hyperspectral image into multiple samples (\emph{from less to more}) to support the efficient training of the network and effectively exploit the spectral correlations among spectrum.

Image Super-Resolution

Learning with Noisy Labels via Sparse Regularization

1 code implementation ICCV 2021 Xiong Zhou, Xianming Liu, Chenyang Wang, Deming Zhai, Junjun Jiang, Xiangyang Ji

In this paper, we theoretically prove that \textbf{any loss can be made robust to noisy labels} by restricting the network output to the set of permutations over a fixed vector.

Learning with noisy labels

Weakly-Supervised Cell Tracking via Backward-and-Forward Propagation

1 code implementation ECCV 2020 Kazuya Nishimura, Junya Hayashida, Chenyang Wang, Dai Fei Elmer Ker, Ryoma Bise

We propose a weakly-supervised cell tracking method that can train a convolutional neural network (CNN) by using only the annotation of "cell detection" (i. e., the coordinates of cell positions) without association information, in which cell positions can be easily obtained by nuclear staining.

Cell Detection Cell Tracking

Jointly Learning Explainable Rules for Recommendation with Knowledge Graph

1 code implementation9 Mar 2019 Weizhi Ma, Min Zhang, Yue Cao, Woojeong, Jin, Chenyang Wang, Yiqun Liu, Shaoping Ma, Xiang Ren

The framework encourages two modules to complement each other in generating effective and explainable recommendation: 1) inductive rules, mined from item-centric knowledge graphs, summarize common multi-hop relational patterns for inferring different item associations and provide human-readable explanation for model prediction; 2) recommendation module can be augmented by induced rules and thus have better generalization ability dealing with the cold-start issue.

Explainable Recommendation Knowledge Graphs +1

In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning

no code implementations19 Sep 2018 Xiaofei Wang, Yiwen Han, Chenyang Wang, Qiyang Zhao, Xu Chen, Min Chen

In order to bring more intelligence to the edge systems, compared to traditional optimization methodology, and driven by the current deep learning techniques, we propose to integrate the Deep Reinforcement Learning techniques and Federated Learning framework with the mobile edge systems, for optimizing the mobile edge computing, caching and communication.

Edge-computing Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.