Search Results for author: Dawei Sun

Found 12 papers, 4 papers with code

On Attack Detection and Identification for the Cyber-Physical System using Lifted System Model

no code implementations8 Dec 2022 Dawei Sun, Minhyun Cho, Inseok Hwang

Motivated by the safety and security issues related to cyber-physical systems with potentially multi-rate, delayed, and nonuniformly sampled measurements, we investigate the attack detection and identification using the lifted system model in this paper.

DistPro: Searching A Fast Knowledge Distillation Process via Meta Optimization

no code implementations12 Apr 2022 Xueqing Deng, Dawei Sun, Shawn Newsam, Peng Wang

Specifically, given a pair of student and teacher networks, DistPro first sets up a rich set of KD connection from the transmitting layers of the teacher to the receiving layers of the student, and in the meanwhile, various transforms are also proposed for comparing feature maps along its pathway for the distillation.

Knowledge Distillation Meta-Learning

Cooperative Task and Motion Planning for Multi-Arm Assembly Systems

no code implementations4 Mar 2022 Jingkai Chen, Jiaoyang Li, Yijiang Huang, Caelan Garrett, Dawei Sun, Chuchu Fan, Andreas Hofmann, Caitlin Mueller, Sven Koenig, Brian C. Williams

Multi-robot assembly systems are becoming increasingly appealing in manufacturing due to their ability to automatically, flexibly, and quickly construct desired structural designs.

Motion Planning Multi-Agent Path Finding +1

SABLAS: Learning Safe Control for Black-box Dynamical Systems

1 code implementation6 Jan 2022 Zengyi Qin, Dawei Sun, Chuchu Fan

Control certificates based on barrier functions have been a powerful tool to generate probably safe control policies for dynamical systems.

Reinforcement Learning (RL)

Learning Density Distribution of Reachable States for Autonomous Systems

no code implementations14 Sep 2021 Yue Meng, Dawei Sun, Zeng Qiu, Md Tawhid Bin Waez, Chuchu Fan

State density distribution, in contrast to worst-case reachability, can be leveraged for safety-related problems to better quantify the likelihood of the risk for potentially hazardous situations.

Knowledge Transfer via Dense Cross-Layer Mutual-Distillation

1 code implementation ECCV 2020 Anbang Yao, Dawei Sun

Knowledge Distillation (KD) based methods adopt the one-way Knowledge Transfer (KT) scheme in which training a lower-capacity student network is guided by a pre-trained high-capacity teacher network.

Knowledge Distillation Representation Learning +1

Verification and Parameter Synthesis for Stochastic Systems using Optimistic Optimization

no code implementations4 Nov 2019 Negin Musavi, Dawei Sun, Sayan Mitra, Geir Dullerud, Sanjay Shakkottai

As a consequence, we obtain theoretical regret bounds on sample efficiency of our solution that depends on key problem parameters like smoothness, near-optimality dimension, and batch size.

Learning Two-View Correspondences and Geometry Using Order-Aware Network

1 code implementation ICCV 2019 Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao

First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.

Vocal Bursts Valence Prediction

Deeply-supervised Knowledge Synergy

1 code implementation CVPR 2019 Dawei Sun, Anbang Yao, Aojun Zhou, Hao Zhao

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet.

General Classification Image Classification

SnapQuant: A Probabilistic and Nested Parameterization for Binary Networks

no code implementations27 Sep 2018 Kuan Wang, Hao Zhao, Anbang Yao, Aojun Zhou, Dawei Sun, Yurong Chen

During the training phase, we generate binary weights on-the-fly since what we actually maintain is the policy network, and all the binary weights are used in a burn-after-reading style.

Learn-Memorize-Recall-Reduce A Robotic Cloud Computing Paradigm

no code implementations16 Apr 2017 Shaoshan Liu, Bolin Ding, Jie Tang, Dawei Sun, Zhe Zhang, Grace Tsai, Jean-Luc Gaudiot

The rise of robotic applications has led to the generation of a huge volume of unstructured data, whereas the current cloud infrastructure was designed to process limited amounts of structured data.

Cloud Computing Memorization

Enabling Embedded Inference Engine with ARM Compute Library: A Case Study

no code implementations12 Apr 2017 Dawei Sun, Shaoshan Liu, Jean-Luc Gaudiot

Our conclusion is that, on embedded devices, we most likely will use very simple deep learning models for inference, and with well-developed building blocks such as ACL, it may be better in both performance and development time to build the engine from scratch.

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