Search Results for author: Peng Cheng

Found 34 papers, 11 papers with code

Chinese Grammatical Error Correction Based on Hybrid Models with Data Augmentation

no code implementations AACL (NLP-TEA) 2020 Yi Wang, Ruibin Yuan, Yan‘gen Luo, Yufang Qin, NianYong Zhu, Peng Cheng, Lihuan Wang

A better Chinese Grammatical Error Diagnosis (CGED) system for automatic Grammatical Error Correction (GEC) can benefit foreign Chinese learners and lower Chinese learning barriers.

Data Augmentation Grammatical Error Correction

SurrogatePrompt: Bypassing the Safety Filter of Text-To-Image Models via Substitution

1 code implementation25 Sep 2023 Zhongjie Ba, Jieming Zhong, Jiachen Lei, Peng Cheng, Qinglong Wang, Zhan Qin, Zhibo Wang, Kui Ren

Evaluation results disclose an 88% success rate in bypassing Midjourney's proprietary safety filter with our attack prompts, leading to the generation of counterfeit images depicting political figures in violent scenarios.

ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning

1 code implementation6 Sep 2023 Linkang Du, Min Chen, Mingyang Sun, Shouling Ji, Peng Cheng, Jiming Chen, Zhikun Zhang

In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL.

Autonomous Vehicles Offline RL +1

Masked Diffusion Models Are Fast and Privacy-Aware Learners

1 code implementation20 Jun 2023 Jiachen Lei, Peng Cheng, Zhongjie Ba, Kui Ren

Moreover, our masked pre-training technique can be universally applied to various diffusion models that directly generate images in the pixel space, aiding in the learning of pre-trained models with superior generalizability.

Denoising Image Generation

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

no code implementations7 Jun 2023 Peng Cheng, Xianyuan Zhan, Zhihao Wu, Wenjia Zhang, Shoucheng Song, Han Wang, Youfang Lin, Li Jiang

Based on extensive experiments, we find TSRL achieves great performance on small benchmark datasets with as few as 1% of the original samples, which significantly outperforms the recent offline RL algorithms in terms of data efficiency and generalizability.

Data Augmentation Offline RL +1

Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal

1 code implementation6 Apr 2023 Tao Gao, Yuanbo Wen, Kaihao Zhang, Peng Cheng, Ting Chen

Rain-by-snow weather removal is a specialized task in weather-degraded image restoration aiming to eliminate coexisting rain streaks and snow particles.

Image Restoration

An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context

no code implementations24 Dec 2022 Xiaoyu Chen, Xiangming Zhu, Yufeng Zheng, Pushi Zhang, Li Zhao, Wenxue Cheng, Peng Cheng, Yongqiang Xiong, Tao Qin, Jianyu Chen, Tie-Yan Liu

One of the key challenges in deploying RL to real-world applications is to adapt to variations of unknown environment contexts, such as changing terrains in robotic tasks and fluctuated bandwidth in congestion control.

FedSiam-DA: Dual-aggregated Federated Learning via Siamese Network under Non-IID Data

no code implementations17 Nov 2022 Ming Yang, Yanhan Wang, Xin Wang, Zhenyong Zhang, Xiaoming Wu, Peng Cheng

Federated learning is a distributed learning that allows each client to keep the original data locally and only upload the parameters of the local model to the server.

Contrastive Learning Federated Learning

Stability of Weighted Majority Voting under Estimated Weights

no code implementations13 Jul 2022 Shaojie Bai, Dongxia Wang, Tim Muller, Peng Cheng, Jiming Chen

To formally analyse the uncertainty to the decision process, we introduce and analyse two important properties of such unbiased trust values: stability of correctness and stability of optimality.

Decision Making

Discriminator-Guided Model-Based Offline Imitation Learning

no code implementations1 Jul 2022 Wenjia Zhang, Haoran Xu, Haoyi Niu, Peng Cheng, Ming Li, Heming Zhang, Guyue Zhou, Xianyuan Zhan

In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discriminator to simultaneously distinguish the dynamics correctness and suboptimality of model rollout data against real expert demonstrations.

Imitation Learning

Tutel: Adaptive Mixture-of-Experts at Scale

2 code implementations7 Jun 2022 Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, Joe Chau, Peng Cheng, Fan Yang, Mao Yang, Yongqiang Xiong

On efficiency, Flex accelerates SwinV2-MoE, achieving up to 1. 55x and 2. 11x speedup in training and inference over Fairseq, respectively.

Object Detection

VeriFi: Towards Verifiable Federated Unlearning

no code implementations25 May 2022 Xiangshan Gao, Xingjun Ma, Jingyi Wang, Youcheng Sun, Bo Li, Shouling Ji, Peng Cheng, Jiming Chen

One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.

Federated Learning

Spatio-Temporal-Frequency Graph Attention Convolutional Network for Aircraft Recognition Based on Heterogeneous Radar Network

no code implementations15 Apr 2022 Han Meng, Yuexing Peng, Wenbo Wang, Peng Cheng, Yonghui Li, Wei Xiang

This paper proposes a knowledge-and-data-driven graph neural network-based collaboration learning model for reliable aircraft recognition in a heterogeneous radar network.

Graph Attention

GridTuner: Reinvestigate Grid Size Selection for Spatiotemporal Prediction Models [Technical Report]

no code implementations10 Jan 2022 Jiabao Jin, Peng Cheng, Lei Chen, Xuemin Lin, Wenjie Zhang

In this paper, we study a region partitioning problem, namely optimal grid size selection problem (OGSS), which aims to minimize the real error of spatiotemporal prediction models by selecting the optimal grid size.

Traffic Prediction

Semi-Supervised Domain Generalizable Person Re-Identification

3 code implementations11 Aug 2021 Lingxiao He, Wu Liu, Jian Liang, Kecheng Zheng, Xingyu Liao, Peng Cheng, Tao Mei

Instead, we aim to explore multiple labeled datasets to learn generalized domain-invariant representations for person re-id, which is expected universally effective for each new-coming re-id scenario.

Ranked #16 on Person Re-Identification on Market-1501 (using extra training data)

Generalizable Person Re-identification Knowledge Distillation +1

Dynamic Multi-Scale Loss Optimization for Object Detection

no code implementations9 Aug 2021 Yihao Luo, Xiang Cao, Juntao Zhang, Peng Cheng, Tianjiang Wang, Qi Feng

With the continuous improvement of the performance of object detectors via advanced model architectures, imbalance problems in the training process have received more attention.

object-detection Object Detection

A Queueing-Theoretic Framework for Vehicle Dispatching in Dynamic Car-Hailing [technical report]

no code implementations19 Jul 2021 Peng Cheng, Jiabao Jin, Lei Chen, Xuemin Lin, Libin Zheng

In this paper, we consider an important dynamic car-hailing problem, namely \textit{maximum revenue vehicle dispatching} (MRVD), in which rider requests dynamically arrive and drivers need to serve as many riders as possible such that the entire revenue of the platform is maximized.

CrossoverScheduler: Overlapping Multiple Distributed Training Applications in a Crossover Manner

no code implementations14 Mar 2021 Cheng Luo, Lei Qu, Youshan Miao, Peng Cheng, Yongqiang Xiong

Distributed deep learning workloads include throughput-intensive training tasks on the GPU clusters, where the Distributed Stochastic Gradient Descent (SGD) incurs significant communication delays after backward propagation, forces workers to wait for the gradient synchronization via a centralized parameter server or directly in decentralized workers.

Image Classification

RobOT: Robustness-Oriented Testing for Deep Learning Systems

1 code implementation11 Feb 2021 Jingyi Wang, Jialuo Chen, Youcheng Sun, Xingjun Ma, Dongxia Wang, Jun Sun, Peng Cheng

A key part of RobOT is a quantitative measurement on 1) the value of each test case in improving model robustness (often via retraining), and 2) the convergence quality of the model robustness improvement.

Software Engineering

TrojanZoo: Towards Unified, Holistic, and Practical Evaluation of Neural Backdoors

1 code implementation16 Dec 2020 Ren Pang, Zheng Zhang, Xiangshan Gao, Zhaohan Xi, Shouling Ji, Peng Cheng, Xiapu Luo, Ting Wang

To bridge this gap, we design and implement TROJANZOO, the first open-source platform for evaluating neural backdoor attacks/defenses in a unified, holistic, and practical manner.

UNIFUZZ: A Holistic and Pragmatic Metrics-Driven Platform for Evaluating Fuzzers

1 code implementation5 Oct 2020 Yuwei Li, Shouling Ji, Yuan Chen, Sizhuang Liang, Wei-Han Lee, Yueyao Chen, Chenyang Lyu, Chunming Wu, Raheem Beyah, Peng Cheng, Kangjie Lu, Ting Wang

We hope that our findings can shed light on reliable fuzzing evaluation, so that we can discover promising fuzzing primitives to effectively facilitate fuzzer designs in the future.

Cryptography and Security

Deep Multi-Task Learning for Cooperative NOMA: System Design and Principles

no code implementations27 Jul 2020 Yuxin Lu, Peng Cheng, Zhuo Chen, Wai Ho Mow, Yonghui Li, Branka Vucetic

We develop a novel hybrid-cascaded deep neural network (DNN) architecture such that the entire system can be optimized in a holistic manner.

Multi-Task Learning

FastReID: A Pytorch Toolbox for General Instance Re-identification

2 code implementations4 Jun 2020 Lingxiao He, Xingyu Liao, Wu Liu, Xinchen Liu, Peng Cheng, Tao Mei

General Instance Re-identification is a very important task in the computer vision, which can be widely used in many practical applications, such as person/vehicle re-identification, face recognition, wildlife protection, commodity tracing, and snapshop, etc.. To meet the increasing application demand for general instance re-identification, we present FastReID as a widely used software system in JD AI Research.

Face Recognition Image Retrieval +2

Simulating Performance of ML Systems with Offline Profiling

no code implementations17 Feb 2020 Hongming Huang, Peng Cheng, Hong Xu, Yongqiang Xiong

We advocate that simulation based on offline profiling is a promising approach to better understand and improve the complex ML systems.

False Data Injection Attacks and the Distributed Countermeasure in DC Microgrids

no code implementations7 Jan 2020 Mengxiang Liu, Peng Cheng, Chengcheng Zhao, Ruilong Deng, Wenhai Wang, Jiming Chen

In this paper, we consider a hierarchical control based DC microgrid (DCmG) equipped with unknown input observer (UIO) based detectors, where the potential false data injection (FDI) attacks and the distributed countermeasure are investigated.

Lightweight and Unobtrusive Data Obfuscation at IoT Edge for Remote Inference

1 code implementation20 Dec 2019 Dixing Xu, Mengyao Zheng, Linshan Jiang, Chaojie Gu, Rui Tan, Peng Cheng

Executing deep neural networks for inference on the server-class or cloud backend based on data generated at the edge of Internet of Things is desirable due primarily to the limited compute power of edge devices and the need to protect the confidentiality of the inference neural networks.

Handwritten Digit Recognition Sign Language Recognition

Challenges of Privacy-Preserving Machine Learning in IoT

no code implementations21 Sep 2019 Mengyao Zheng, Dixing Xu, Linshan Jiang, Chaojie Gu, Rui Tan, Peng Cheng

The Internet of Things (IoT) will be a main data generation infrastructure for achieving better system intelligence.

BIG-bench Machine Learning Cloud Computing +1

Privacy-preserving Distributed Machine Learning via Local Randomization and ADMM Perturbation

no code implementations30 Jul 2019 Xin Wang, Hideaki Ishii, Linkang Du, Peng Cheng, Jiming Chen

With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks.

BIG-bench Machine Learning Privacy Preserving

A Learning-Based Two-Stage Spectrum Sharing Strategy with Multiple Primary Transmit Power Levels

no code implementations21 Jul 2019 Rui Zhang, Peng Cheng, Zhuo Chen, Yonghui Li, Branka Vucetic

Then, based on a novel normalized power level alignment metric, we propose two prediction-transmission structures, namely periodic and non-periodic, for spectrum access (the second part in Stage II), which enable the secondary transmitter (ST) to closely follow the PT power level variation.

Fast and Accurate, Convolutional Neural Network Based Approach for Object Detection from UAV

no code implementations16 Aug 2018 Xiaoliang Wang, Peng Cheng, Xinchuan Liu, Benedict Uzochukwu

Unmanned Aerial Vehicles (UAVs), have intrigued different people from all walks of life, because of their pervasive computing capabilities.

Management object-detection +1

Focal Loss Dense Detector for Vehicle Surveillance

no code implementations3 Mar 2018 Xiaoliang Wang, Peng Cheng, Xinchuan Liu, Benedict Uzochukwu

Deep learning has been widely recognized as a promising approach in different computer vision applications.

object-detection Object Detection

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