Search Results for author: Ming Zhao

Found 26 papers, 8 papers with code

Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions

1 code implementation14 Mar 2023 Kaiqi Zhao, Animesh Jain, Ming Zhao

Then, it proposes adaptive pruning policies for automatically meeting the pruning objectives of accuracy-critical, memory-constrained, and latency-sensitive tasks.

A Contrastive Knowledge Transfer Framework for Model Compression and Transfer Learning

1 code implementation14 Mar 2023 Kaiqi Zhao, Yitao Chen, Ming Zhao

Knowledge Transfer (KT) achieves competitive performance and is widely used for image classification tasks in model compression and transfer learning.

Image Classification Model Compression +1

FeSAC: Federated Learning-Based Soft Actor-Critic Traffic Offloading in Space-Air-Ground Integrated Network

no code implementations5 Dec 2022 Fengxiao Tang, Yilin Yang, Xin Yao, Ming Zhao, Nei Kato

To further expand the resource pool of traffic offloading in SAGIN, we extend the single-layer satellite network into a double-layer satellite network composed of low-orbit satellites (LEO) and high-orbit satellites (GEO).

Fairness Federated Learning +2

RGB-X Classification for Electronics Sorting

no code implementations8 Sep 2022 FNU Abhimanyu, Tejas Zodage, Umesh Thillaivasan, Xinyue Lai, Rahul Chakwate, Javier Santillan, Emma Oti, Ming Zhao, Ralph Boirum, Howie Choset, Matthew Travers

Conventional recycling processes rely on shredding and sorting waste streams, but for WEEE, which is comprised of numerous dissimilar materials, we explore targeted disassembly of numerous objects for improved material recovery.

Classification Image Classification

OpenCalib: A Multi-sensor Calibration Toolbox for Autonomous Driving

1 code implementation27 May 2022 Guohang Yan, Liu Zhuochun, Chengjie Wang, Chunlei Shi, Pengjin Wei, Xinyu Cai, Tao Ma, Zhizheng Liu, Zebin Zhong, Yuqian Liu, Ming Zhao, Zheng Ma, Yikang Li

To this end, we present OpenCalib, a calibration toolbox that contains a rich set of various sensor calibration methods.

Autonomous Driving

Leveraging Reaction-aware Substructures for Retrosynthesis Analysis

no code implementations12 Apr 2022 Lei Fang, Junren Li, Ming Zhao, Li Tan, Jian-Guang Lou

In this paper, we propose a substructure-level decoding model, where the substructures are reaction-aware and can be automatically extracted with a fully data-driven approach.

Decision Making Machine Translation +1

RFVTM: A Recovery and Filtering Vertex Trichotomy Matching for Remote Sensing Image Registration

no code implementations2 Apr 2022 Ming Zhao, Bowen An, Yongpeng Wu, Huynh Van Luong, André Kaup

In this paper, a robust feature point matching algorithm called Recovery and Filtering Vertex Trichotomy Matching (RFVTM) is proposed to remove outliers and retain sufficient inliers for remote sensing images.

Image Registration

Automatic Registration of Images with Inconsistent Content Through Line-Support Region Segmentation and Geometrical Outlier Removal

no code implementations2 Apr 2022 Ming Zhao, Yongpeng Wu, Shengda Pan, Fan Zhou, Bowen An, André Kaup

This new approach is designed to address the problems associated with the registration of images with affine deformations and inconsistent content, such as remote sensing images with different spectral content or noise interference, or map images with inconsistent annotations.

Image Registration

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

1 code implementation CVPR 2022 Zhigang Jiang, Zhongzheng Xiang, Jinhua Xu, Ming Zhao

We present that using horizon-depth along with room height can obtain omnidirectional-geometry awareness of room layout in both horizontal and vertical directions.

Room Layout Estimation

Enabling Deep Learning on Edge Devices through Filter Pruning and Knowledge Transfer

no code implementations22 Jan 2022 Kaiqi Zhao, Yitao Chen, Ming Zhao

The results show that 1) our model compression method can remove up to 99. 36% parameters of WRN-28-10, while preserving a Top-1 accuracy of over 90% on CIFAR-10; 2) our knowledge transfer method enables the compressed models to achieve more than 90% accuracy on CIFAR-10 and retain good accuracy on old categories; 3) it allows the compressed models to converge within real time (three to six minutes) on the edge for incremental learning tasks; 4) it enables the model to classify unseen categories of data (78. 92% Top-1 accuracy) that it is never trained with.

Image Classification Incremental Learning +4

Iterative Activation-based Structured Pruning

no code implementations22 Jan 2022 Kaiqi Zhao, Animesh Jain, Ming Zhao

To solve this problem, we propose two activation-based pruning methods, Iterative Activation-based Pruning (IAP) and Adaptive Iterative Activation-based Pruning (AIAP).

Adaptive Activation-based Structured Pruning

1 code implementation21 Jan 2022 Kaiqi Zhao, Animesh Jain, Ming Zhao

Pruning is a promising approach to compress complex deep learning models in order to deploy them on resource-constrained edge devices.

MIC: Model-agnostic Integrated Cross-channel Recommenders

no code implementations22 Oct 2021 Yujie Lu, Ping Nie, Shengyu Zhang, Ming Zhao, Ruobing Xie, William Yang Wang, Yi Ren

However, existing work are primarily built upon pre-defined retrieval channels, including User-CF (U2U), Item-CF (I2I), and Embedding-based Retrieval (U2I), thus access to the limited correlation between users and items which solely entail from partial information of latent interactions.

Recommendation Systems Retrieval +2

Generative adversarial network based single pixel imaging

no code implementations11 Jul 2021 Ming Zhao, Fengqiang Li, Fengyue Huo, Zhiming Tian

Single pixel imaging can reconstruct two-dimensional images of a scene with only a single-pixel detector.

SEOVER: Sentence-level Emotion Orientation Vector based Conversation Emotion Recognition Model

no code implementations16 Jun 2021 Zaijing Li, Fengxiao Tang, Tieyu Sun, Yusen Zhu, Ming Zhao

For the task of conversation emotion recognition, recent works focus on speaker relationship modeling but ignore the role of utterance's emotional tendency. In this paper, we propose a new expression paradigm of sentence-level emotion orientation vector to model the potential correlation of emotions between sentence vectors.

Emotion Recognition Language Modelling +1

On the Evaluation of Vision-and-Language Navigation Instructions

no code implementations EACL 2021 Ming Zhao, Peter Anderson, Vihan Jain, Su Wang, Alexander Ku, Jason Baldridge, Eugene Ie

Vision-and-Language Navigation wayfinding agents can be enhanced by exploiting automatically generated navigation instructions.

Vision and Language Navigation

Knowledge-Driven Machine Learning: Concept, Model and Case Study on Channel Estimation

no code implementations21 Dec 2020 Daofeng Li, Kaihe Deng, Ming Zhao, Sihai Zhang, Jinkang Zhu

The power of big data and machine learning has been drastically demonstrated in many fields during the past twenty years which somehow leads to the vague even false understanding that the huge amount of precious human knowledge accumulated to date no longer seems to matter.

BIG-bench Machine Learning

A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus

no code implementations18 Nov 2020 BoWen Zhang, Hexiang Hu, Joonseok Lee, Ming Zhao, Sheide Chammas, Vihan Jain, Eugene Ie, Fei Sha

Identifying a short segment in a long video that semantically matches a text query is a challenging task that has important application potentials in language-based video search, browsing, and navigation.

Language Modelling Masked Language Modeling +3

Wireless Communication Based on Microwave Photon-Level Detection With Superconducting Devices: Achievable Rate Prediction

no code implementations25 Jun 2020 Junyu Zhang, Chen Gong, Shangbin Li, Rui Ni, Chengjie Zuo, Jinkang Zhu, Ming Zhao, Zhengyuan Xu

Future wireless communication system embraces physical-layer signal detection with high sensitivity, especially in the microwave photon level.

Weak Radio Frequency Signal Detection Based on Piezo-Opto-Electro-Mechanical System: Architecture Design and Sensitivity Prediction

no code implementations29 Mar 2020 Shanchi Wu, Chen Gong, Chengjie Zuo, Shangbin Li, Junyu Zhang, Zhongbin Dai, Kai Yang, Ming Zhao, Rui Ni, Zhengyuan Xu, Jinkang Zhu

We propose a novel radio-frequency (RF) receiving architecture based on micro-electro-mechanical system (MEMS) and optical coherent detection module.

Semi-Federated Learning

1 code implementation28 Mar 2020 Zhikun Chen, Daofeng Li, Ming Zhao, Sihai Zhang, Jinkang Zhu

Federated learning (FL) enables massive distributed Information and Communication Technology (ICT) devices to learn a global consensus model without any participants revealing their own data to the central server.

Federated Learning

Progressive Layered Extraction (PLE): A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations

4 code implementations RecSys 2020 Hongyan Tang, Junning Liu, Ming Zhao, Xudong Gong

Moreover, through extensive experiments across SOTA MTL models, we have observed an interesting seesaw phenomenon that performance of one task is often improved by hurting the performance of some other tasks.

Click-Through Rate Prediction Multi-Task Learning +2

A comprehensive review on convolutional neural network in machine fault diagnosis

no code implementations13 Feb 2020 Jinyang Jiao, Ming Zhao, Jing Lin, Kaixuan Liang

To fill in this gap, this work attempts to review and summarize the development of the Convolutional Network based Fault Diagnosis (CNFD) approaches comprehensively.

Decision Making

Detection of a Westward Hotspot Offset in the Atmosphere of a Hot Gas Giant CoRoT-2b

1 code implementation19 Jan 2018 Lisa Dang, Nicolas B. Cowan, Joel C. Schwartz, Emily Rauscher, Michael Zhang, Heather A. Knutson, Michael Line, Ian Dobbs-Dixon, Drake Deming, Sudarsan Sundararajan, Jonathan J. Fortney, Ming Zhao

The peculiar infrared flux map of CoRoT-2b may result from westward winds due to non-synchronous rotation magnetic effects, or partial cloud coverage, that obscures the emergent flux from the planet's eastern hemisphere.

Earth and Planetary Astrophysics

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