Search Results for author: Xinyi Zhang

Found 16 papers, 6 papers with code

基于自动识别的委婉语历时性发展变化与社会共变研究(A Study on the Diachronic Development and Social Covariance of Euphemism Based on Automatic Recognition)

no code implementations CCL 2021 Chenlin Zhang, Mingwen Wang, Yiming Tan, Ming Yin, Xinyi Zhang

“本文主要以汉语委婉语作为研究对象, 基于大量人工标注, 借助机器学习有监督分类方法, 实现了较高精度的委婉语自动识别, 并基于此对1946年-2017年的《人民日报》中的委婉语历时变化发展情况进行量化统计分析。从大规模数据的角度探讨委婉语历时性发展变化、委婉语与社会之间的共变关系, 验证了语言的格雷什姆规律与更新规律。”

H2H: Heterogeneous Model to Heterogeneous System Mapping with Computation and Communication Awareness

1 code implementation29 Apr 2022 Xinyi Zhang, Cong Hao, Peipei Zhou, Alex Jones, Jingtong Hu

The heterogeneity in ML models comes from multi-sensor perceiving and multi-task learning, i. e., multi-modality multi-task (MMMT), resulting in diverse deep neural network (DNN) layers and computation patterns.

Multi-Task Learning

EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization

no code implementations18 Feb 2022 Yue Tang, Xinyi Zhang, Peipei Zhou, Jingtong Hu

In this work, we design EF-Train, an efficient DNN training accelerator with a unified channel-level parallelism-based convolution kernel that can achieve end-to-end training on resource-limited low-power edge-level FPGAs.

Domain Adaptation

Speech Technology for Everyone: Automatic Speech Recognition for Non-Native English with Transfer Learning

no code implementations1 Oct 2021 Toshiko Shibano, Xinyi Zhang, Mia Taige Li, Haejin Cho, Peter Sullivan, Muhammad Abdul-Mageed

To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2. 0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al., 2018) under different training settings.

Automatic Speech Recognition Transfer Learning

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

no code implementations CVPR 2021 Xinyi Zhang, Hang Dong, Jinshan Pan, Chao Zhu, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Fei Wang

On the other hand, the video dehazing algorithms, which can acquire more satisfying dehazing results by exploiting the temporal redundancy from neighborhood hazy frames, receive less attention due to the absence of the video dehazing datasets.

Image Dehazing

Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack

no code implementations13 Apr 2021 Xinyi Zhang, Chengfang Fang, Jie Shi

We find the effectiveness of existing techniques significantly affected by the absence of pre-trained models.

Model extraction

mSHINE: A Multiple-meta-paths Simultaneous Learning Framework for Heterogeneous Information Network Embedding

1 code implementation6 Apr 2021 Xinyi Zhang, Lihui Chen

To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths.

Link Prediction Network Embedding +1

LA-HCN: Label-based Attention for Hierarchical Multi-label TextClassification Neural Network

no code implementations23 Sep 2020 Xinyi Zhang, Jiahao Xu, Charlie Soh, Lihui Chen

In this paper, we propose a Label-based Attention for Hierarchical Mutlti-label Text Classification Neural Network (LA-HCN), where the novel label-based attention module is designed to hierarchically extract important information from the text based on the labels from different hierarchy levels.

Multi Label Text Classification Multi-Label Text Classification

HEU Emotion: A Large-scale Database for Multi-modal Emotion Recognition in the Wild

no code implementations24 Jul 2020 Jing Chen, Chenhui Wang, Kejun Wang, Chaoqun Yin, Cong Zhao, Tao Xu, Xinyi Zhang, Ziqiang Huang, Meichen Liu, Tao Yang

Existing multimodal emotion databases in the real-world conditions are few and small, with a limited number of subjects and expressed in a single language.

Emotion Recognition Facial Expression Recognition

Multi-Scale Boosted Dehazing Network with Dense Feature Fusion

1 code implementation CVPR 2020 Hang Dong, Jinshan Pan, Lei Xiang, Zhe Hu, Xinyi Zhang, Fei Wang, Ming-Hsuan Yang

To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme.

Gated Fusion Network for Degraded Image Super Resolution

1 code implementation2 Mar 2020 Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang

To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately.

Frame Image Super-Resolution

Baconian: A Unified Open-source Framework for Model-Based Reinforcement Learning

2 code implementations23 Apr 2019 Linsen Dong, Guanyu Gao, Xinyi Zhang, Liang-Yu Chen, Yonggang Wen

Model-Based Reinforcement Learning (MBRL) is one category of Reinforcement Learning (RL) algorithms which can improve sampling efficiency by modeling and approximating system dynamics.

Autonomous Driving Model-based Reinforcement Learning +1

Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search

no code implementations31 Jan 2019 Weiwen Jiang, Xinyi Zhang, Edwin H. -M. Sha, Lei Yang, Qingfeng Zhuge, Yiyu Shi, Jingtong Hu

In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.

Neural Architecture Search

Gated Fusion Network for Joint Image Deblurring and Super-Resolution

2 code implementations27 Jul 2018 Xinyi Zhang, Hang Dong, Zhe Hu, Wei-Sheng Lai, Fei Wang, Ming-Hsuan Yang

Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution.

Deblurring Frame +2

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