Search Results for author: Siyu Chen

Found 38 papers, 11 papers with code

Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence

2 code implementations23 Aug 2017 Xin Jin, Le Wu, Xiao-Dong Li, Siyu Chen, Siwei Peng, Jingying Chi, Shiming Ge, Chenggen Song, Geng Zhao

Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization).

Visualization of Hyperspectral Images Using Moving Least Squares

no code implementations20 Jan 2018 Danping Liao, Siyu Chen, Yuntao Qian

The matching pixels between a pair of HSI and RGB image can be reused to display other HSIs captured b the same imaging sensor with natural colors.

Spectral Image Visualization Using Generative Adversarial Networks

no code implementations7 Feb 2018 Siyu Chen, Danping Liao, Yuntao Qian

The adversarial loss pushes our solution to the natural image distribution using a discriminator network that is trained to differentiate between false-color images and natural-color images.

Generative Adversarial Network

Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature Representation

no code implementations16 Apr 2019 Jingzhou Chen, Siyu Chen, Peilin Zhou, Yuntao Qian

Secondly, in order to utilize the local spatial correlation among pixels, we share the previous subnetwork as a spectral feature extractor for each pixel in a patch of image, after which the spectral features of all pixels in a patch are combined and feeded into the subsequent classification subnetwork.

Classification General Classification +1

A Deep Optimization Approach for Image Deconvolution

no code implementations16 Apr 2019 Zhijian Luo, Siyu Chen, Yuntao Qian

In blind image deconvolution, priors are often leveraged to constrain the solution space, so as to alleviate the under-determinacy.

Image Deconvolution

Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems

no code implementations28 May 2019 Tianle Cai, Ruiqi Gao, Jikai Hou, Siyu Chen, Dong Wang, Di He, Zhihua Zhang, Li-Wei Wang

First-order methods such as stochastic gradient descent (SGD) are currently the standard algorithm for training deep neural networks.

regression Second-order methods

Defective Convolutional Layers Learn Robust CNNs

no code implementations25 Sep 2019 Tiange Luo, Tianle Cai, Xiaomeng Zhang, Siyu Chen, Di He, LiWei Wang

We first show that predictions made by the defective CNN are less dependent on textural information, but more on shape information, and further find that adversarial examples generated by the defective CNN appear to have semantic shapes.

Defective Convolutional Networks

1 code implementation19 Nov 2019 Tiange Luo, Tianle Cai, Mengxiao Zhang, Siyu Chen, Di He, Li-Wei Wang

Robustness of convolutional neural networks (CNNs) has gained in importance on account of adversarial examples, i. e., inputs added as well-designed perturbations that are imperceptible to humans but can cause the model to predict incorrectly.

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

3 code implementations CVPR 2021 Junting Pan, Siyu Chen, Mike Zheng Shou, Yu Liu, Jing Shao, Hongsheng Li

We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.

Action Detection Action Recognition +5

1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020

2 code implementations16 Jun 2020 Siyu Chen, Junting Pan, Guanglu Song, Manyuan Zhang, Hao Shao, Ziyi Lin, Jing Shao, Hongsheng Li, Yu Liu

This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.

Relation Network Spatio-Temporal Action Localization +1

Market Design for Tradable Mobility Credits

no code implementations3 Jan 2021 Siyu Chen, Ravi Seshadri, Carlos Lima Azevedo, Arun P. Akkinepally, Renming Liu, Andrea Araldo, Yu Jiang, Moshe E. Ben-Akiva

Further, it is more robust in the presence of forecasting errors and non-recurrent events due to the adaptiveness of the market.

Management

Probing $μ$eV ALPs with future LHAASO observation of AGN $γ$-ray spectra

no code implementations25 Jan 2021 Guangbo Long, Siyu Chen, Shuo Xu, Hong-Hao Zhang

For $g_{a\gamma}\gtrsim 2\times$$10^{-11} \rm GeV^{-1}$ with $m_{a}\lesssim0. 5\,\mu$eV, the flux at around 100\, TeV predicted by the ALP model can be enhanced more than an order of magnitude than that from the standard absorption, and could be detected by LHAASO.

High Energy Astrophysical Phenomena Cosmology and Nongalactic Astrophysics High Energy Physics - Phenomenology

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis

2 code implementations CVPR 2021 Yinan He, Bei Gan, Siyu Chen, Yichun Zhou, Guojun Yin, Luchuan Song, Lu Sheng, Jing Shao, Ziwei Liu

To counter this emerging threat, we construct the ForgeryNet dataset, an extremely large face forgery dataset with unified annotations in image- and video-level data across four tasks: 1) Image Forgery Classification, including two-way (real / fake), three-way (real / fake with identity-replaced forgery approaches / fake with identity-remained forgery approaches), and n-way (real and 15 respective forgery approaches) classification.

Benchmarking Classification +2

INTERN: A New Learning Paradigm Towards General Vision

no code implementations16 Nov 2021 Jing Shao, Siyu Chen, Yangguang Li, Kun Wang, Zhenfei Yin, Yinan He, Jianing Teng, Qinghong Sun, Mengya Gao, Jihao Liu, Gengshi Huang, Guanglu Song, Yichao Wu, Yuming Huang, Fenggang Liu, Huan Peng, Shuo Qin, Chengyu Wang, Yujie Wang, Conghui He, Ding Liang, Yu Liu, Fengwei Yu, Junjie Yan, Dahua Lin, Xiaogang Wang, Yu Qiao

Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.

Wasserstein Flow Meets Replicator Dynamics: A Mean-Field Analysis of Representation Learning in Actor-Critic

no code implementations NeurIPS 2021 Yufeng Zhang, Siyu Chen, Zhuoran Yang, Michael I. Jordan, Zhaoran Wang

Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates.

Representation Learning

X-Learner: Learning Cross Sources and Tasks for Universal Visual Representation

no code implementations16 Mar 2022 Yinan He, Gengshi Huang, Siyu Chen, Jianing Teng, Wang Kun, Zhenfei Yin, Lu Sheng, Ziwei Liu, Yu Qiao, Jing Shao

2) Squeeze Stage: X-Learner condenses the model to a reasonable size and learns the universal and generalizable representation for various tasks transferring.

object-detection Object Detection +3

Few-shot Forgery Detection via Guided Adversarial Interpolation

no code implementations12 Apr 2022 Haonan Qiu, Siyu Chen, Bei Gan, Kun Wang, Huafeng Shi, Jing Shao, Ziwei Liu

Notably, our method is also validated to be robust to choices of majority and minority forgery approaches.

The planted XY model: thermodynamics and inference

no code implementations12 Aug 2022 Siyu Chen, Guanhao Huang, Giovanni Piccioli, Lenka Zdeborová

We derive the replica symmetric (RS) phase diagram in the temperature, ferromagnetic bias plane using the approximate message passing (AMP) algorithm and its state evolution (SE).

A Spatiotemporal Model for Precise and Efficient Fully-automatic 3D Motion Correction in OCT

no code implementations15 Sep 2022 Stefan Ploner, Siyu Chen, Jungeun Won, Lennart Husvogt, Katharina Breininger, Julia Schottenhamml, James Fujimoto, Andreas Maier

Optical coherence tomography (OCT) is a micrometer-scale, volumetric imaging modality that has become a clinical standard in ophthalmology.

Super-Resolution

SoccerNet 2022 Challenges Results

7 code implementations5 Oct 2022 Silvio Giancola, Anthony Cioppa, Adrien Deliège, Floriane Magera, Vladimir Somers, Le Kang, Xin Zhou, Olivier Barnich, Christophe De Vleeschouwer, Alexandre Alahi, Bernard Ghanem, Marc Van Droogenbroeck, Abdulrahman Darwish, Adrien Maglo, Albert Clapés, Andreas Luyts, Andrei Boiarov, Artur Xarles, Astrid Orcesi, Avijit Shah, Baoyu Fan, Bharath Comandur, Chen Chen, Chen Zhang, Chen Zhao, Chengzhi Lin, Cheuk-Yiu Chan, Chun Chuen Hui, Dengjie Li, Fan Yang, Fan Liang, Fang Da, Feng Yan, Fufu Yu, Guanshuo Wang, H. Anthony Chan, He Zhu, Hongwei Kan, Jiaming Chu, Jianming Hu, Jianyang Gu, Jin Chen, João V. B. Soares, Jonas Theiner, Jorge De Corte, José Henrique Brito, Jun Zhang, Junjie Li, Junwei Liang, Leqi Shen, Lin Ma, Lingchi Chen, Miguel Santos Marques, Mike Azatov, Nikita Kasatkin, Ning Wang, Qiong Jia, Quoc Cuong Pham, Ralph Ewerth, Ran Song, RenGang Li, Rikke Gade, Ruben Debien, Runze Zhang, Sangrok Lee, Sergio Escalera, Shan Jiang, Shigeyuki Odashima, Shimin Chen, Shoichi Masui, Shouhong Ding, Sin-wai Chan, Siyu Chen, Tallal El-Shabrawy, Tao He, Thomas B. Moeslund, Wan-Chi Siu, Wei zhang, Wei Li, Xiangwei Wang, Xiao Tan, Xiaochuan Li, Xiaolin Wei, Xiaoqing Ye, Xing Liu, Xinying Wang, Yandong Guo, YaQian Zhao, Yi Yu, YingYing Li, Yue He, Yujie Zhong, Zhenhua Guo, Zhiheng Li

The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.

Action Spotting Camera Calibration +3

DiP: Learning Discriminative Implicit Parts for Person Re-Identification

1 code implementation24 Dec 2022 Dengjie Li, Siyu Chen, Yujie Zhong, Lin Ma

In person re-identification (ReID) tasks, many works explore the learning of part features to improve the performance over global image features.

Person Re-Identification Position

Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model

no code implementations15 Mar 2023 Siyu Chen, Jibang Wu, Yifan Wu, Zhuoran Yang

Such a problem is modeled as a Stackelberg game between the principal and the agent, where the principal announces a scoring rule that specifies the payment, and then the agent then chooses an effort level that maximizes her own profit and reports the information.

A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observations

no code implementations20 Mar 2023 Siyu Chen, Yitan Wang, Zhaoran Wang, Zhuoran Yang

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data.

Unsupervised detection of small hyperreflective features in ultrahigh resolution optical coherence tomography

no code implementations26 Mar 2023 Marcel Reimann, Jungeun Won, Hiroyuki Takahashi, Antonio Yaghy, Yunchan Hwang, Stefan Ploner, Junhong Lin, Jessica Girgis, Kenneth Lam, Siyu Chen, Nadia K. Waheed, Andreas Maier, James G. Fujimoto

Recent advances in optical coherence tomography such as the development of high speed ultrahigh resolution scanners and corresponding signal processing techniques may reveal new potential biomarkers in retinal diseases.

Image Quality-aware Diagnosis via Meta-knowledge Co-embedding

1 code implementation CVPR 2023 Haoxuan Che, Siyu Chen, Hao Chen

Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models.

Image Quality Assessment Meta-Learning

Adaptive Parameter Estimation under Finite Excitation

no code implementations22 May 2023 Siyu Chen, Jing Na, Yingbo Huang

And it is given that the theoretical analysis of the proposed method in stability and robustness.

Actions Speak What You Want: Provably Sample-Efficient Reinforcement Learning of the Quantal Stackelberg Equilibrium from Strategic Feedbacks

no code implementations26 Jul 2023 Siyu Chen, Mengdi Wang, Zhuoran Yang

The goal of the leader is to find her optimal policy, which yields the optimal expected total return, by interacting with the follower and learning from data.

Decision Making LEMMA +1

Context Matters: Data-Efficient Augmentation of Large Language Models for Scientific Applications

1 code implementation12 Dec 2023 Xiang Li, Haoran Tang, Siyu Chen, Ziwei Wang, Anurag Maravi, Marcin Abram

In this paper, we explore the challenges inherent to Large Language Models (LLMs) like GPT-4, particularly their propensity for hallucinations, logic mistakes, and incorrect conclusions when tasked with answering complex questions.

Cooperative Learning with Gaussian Processes for Euler-Lagrange Systems Tracking Control under Switching Topologies

no code implementations5 Feb 2024 Zewen Yang, Songbo Dong, Armin Lederer, Xiaobing Dai, Siyu Chen, Stefan Sosnowski, Georges Hattab, Sandra Hirche

This work presents an innovative learning-based approach to tackle the tracking control problem of Euler-Lagrange multi-agent systems with partially unknown dynamics operating under switching communication topologies.

Gaussian Processes

Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality

no code implementations29 Feb 2024 Siyu Chen, Heejune Sheen, Tianhao Wang, Zhuoran Yang

In addition, we prove that an interesting "task allocation" phenomenon emerges during the gradient flow dynamics, where each attention head focuses on solving a single task of the multi-task model.

In-Context Learning

Implicit Regularization of Gradient Flow on One-Layer Softmax Attention

no code implementations13 Mar 2024 Heejune Sheen, Siyu Chen, Tianhao Wang, Harrison H. Zhou

Under a separability assumption on the data, we show that when gradient flow achieves the minimal loss value, it further implicitly minimizes the nuclear norm of the product of the key and query weight matrices.

先秦词网构建及梵汉对比研究(The Construction of Pre-Qin Ancient Chinese WordNet and Cross Language Comparative Study between Ancient Sanskrit WordNet and Pre-Qin Ancient Chinese WordNet)

no code implementations CCL 2021 Xuehui Lu, Huidan Xu, Siyu Chen, Bin Li

“先秦汉语在汉语史研究上具有重要地位, 然而以往的研究始终没有形成结构化的先秦词汇资源, 难以满足古汉语信息处理和跨语言对比的研究需要。国际上以英文词网(WordNet)的义类架构为基础, 已经建立了数十种语言的词网, 已经成为多语言自然语言处理和跨语言对比的基础资源。本文综述了国内外各种词网的构建情况, 特别是古代语言的词网和汉语词网, 然后详细介绍了先秦词网的构建和校正过程, 构建起了涵盖43591个词语、61227个义项、17975个义类的先秦汉语词网。本文还通过与古梵语词网的跨语言对比, 尝试分析这两种古老语言在词汇上的共性和差异, 初步验证先秦词网的有效性。”

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