Search Results for author: Wei Luo

Found 35 papers, 8 papers with code

Mutual-Learning Improves End-to-End Speech Translation

no code implementations EMNLP 2021 Jiawei Zhao, Wei Luo, Boxing Chen, Andrew Gilman

In this paper, we propose an alternative–a trainable mutual-learning scenario, where the MT and the ST models are collaboratively trained and are considered as peers, rather than teacher/student.

Knowledge Distillation Machine Translation +1

IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency

no code implementations16 May 2024 Linshan Hou, Ruili Feng, Zhongyun Hua, Wei Luo, Leo Yu Zhang, Yiming Li

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training.

WaveSleepNet: An Interpretable Network for Expert-like Sleep Staging

no code implementations11 Apr 2024 Yan Pei, Wei Luo

The feature representation of an input signal is segmented into patches within the latent space, each of which is compared against the learned wave prototypes.

Decision Making Sleep Staging

Neural Image Compression with Quantization Rectifier

no code implementations25 Mar 2024 Wei Luo, Bo Chen

This paper presents a novel quantization rectifier (QR) method for image compression that leverages image feature correlation to mitigate the impact of quantization.

Feature Correlation Image Compression +2

MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline

1 code implementation16 Jan 2024 Minpeng Liao, Wei Luo, Chengxi Li, Jing Wu, Kai Fan

Large language models (LLMs) have seen considerable advancements in natural language understanding tasks, yet there remains a gap to bridge before attaining true artificial general intelligence, especially concerning shortcomings in mathematical reasoning capabilities.

GSM8K Math +2

Pre-trained Large Language Models for Financial Sentiment Analysis

1 code implementation10 Jan 2024 Wei Luo, Dihong Gong

Financial sentiment analysis refers to classifying financial text contents into sentiment categories (e. g. positive, negative, and neutral).

Sentiment Analysis

Powerformer: A Section-adaptive Transformer for Power Flow Adjustment

no code implementations5 Jan 2024 KaiXuan Chen, Wei Luo, Shunyu Liu, Yaoquan Wei, Yihe Zhou, Yunpeng Qing, Quan Zhang, Jie Song, Mingli Song

In this paper, we present a novel transformer architecture tailored for learning robust power system state representations, which strives to optimize power dispatch for the power flow adjustment across different transmission sections.

Adaptive Policy with Wait-$k$ Model for Simultaneous Translation

no code implementations23 Oct 2023 Libo Zhao, Kai Fan, Wei Luo, Jing Wu, Shushu Wang, Ziqian Zeng, Zhongqiang Huang

Simultaneous machine translation (SiMT) requires a robust read/write policy in conjunction with a high-quality translation model.

Machine Translation Translation

Dual Effects of the US-China Trade War and COVID-19 on United States Imports: Transfer of China's industrial chain?

no code implementations5 Sep 2023 Wei Luo, Siyuan Kang, Sheng Hu, Lixian Su, Rui Dai

However, the worldwide lockdowns over pandemic have reversed this trend as, over this period, the U. S. effectively imported more goods directly from China and indirectly through Southeast Asian exporters that imported from China.

Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?

no code implementations20 May 2023 Bing Liu, Wei Luo, Gang Li, Jing Huang, Bo Yang

As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks.

Decoder Time Series

Visual Anomaly Detection via Dual-Attention Transformer and Discriminative Flow

no code implementations31 Mar 2023 Haiming Yao, Wei Luo, Wenyong Yu

In this paper, we introduce the novel state-of-the-art Dual-attention Transformer and Discriminative Flow (DADF) framework for visual anomaly detection.

Anomaly Detection

One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization

1 code implementation28 Mar 2023 Deze Wang, Boxing Chen, Shanshan Li, Wei Luo, Shaoliang Peng, Wei Dong, Xiangke Liao

To alleviate the potentially catastrophic forgetting issue in multilingual models, we fix all pre-trained model parameters, insert the parameter-efficient structure adapter, and fine-tune it.

Code Search Code Summarization

Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection

no code implementations10 Mar 2023 Haiming Yao, Wenyong Yu, Wei Luo, Zhenfeng Qiang, Donghao Luo, Xiaotian Zhang

To address this issue, we propose a two-branch approach that consists of a local branch for detecting structural anomalies and a global branch for detecting logical anomalies.

Anomaly Detection

CyberLoc: Towards Accurate Long-term Visual Localization

no code implementations6 Jan 2023 Liu Liu, Yukai Lin, Xiao Liang, Qichao Xu, Miao Jia, Yangdong Liu, Yuxiang Wen, Wei Luo, Jiangwei Li

Second, a single-image-based localization pipeline (retrieval--matching--PnP) is performed to estimate 6-DoF camera poses for each query image, one for each 3D map.

Autonomous Driving Image-Based Localization +3

Normal Reference Attention and Defective Feature Perception Network for Surface Defect Detection

no code implementations18 Nov 2022 Wei Luo, Haiming Yao, Wenyong Yu

Unlike most reconstruction-based methods, our NDP-Net first employs an encoding module that extracts multi scale discriminative features of the surface textures, which is augmented with the defect discriminative ability by the proposed artificial defects and the novel pixel-level defect perception loss.

Anomaly Detection Defect Detection

Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation

1 code implementation18 Oct 2022 Chen Wang, Yuchen Liu, Boxing Chen, Jiajun Zhang, Wei Luo, Zhongqiang Huang, Chengqing Zong

Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Clear Memory-Augmented Auto-Encoder for Surface Defect Detection

no code implementations8 Aug 2022 Wei Luo, Tongzhi Niu, Lixin Tang, Wenyong Yu, Bin Li

At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds.

Anomaly Detection Defect Detection

Feature Transformation for Cross-domain Few-shot Remote Sensing Scene Classification

no code implementations4 Mar 2022 Qiaoling Chen, Zhihao Chen, Wei Luo

Moreover, FTM can be effectively learned on target domain in the case of few training data available and is agnostic to specific network structures.

Cross-Domain Few-Shot Scene Classification

Robust Neural Regression via Uncertainty Learning

no code implementations12 Oct 2021 Akib Mashrur, Wei Luo, Nayyar A. Zaidi, Antonio Robles-Kelly

Deep neural networks tend to underestimate uncertainty and produce overly confident predictions.


Distributed Optimization of Graph Convolutional Network using Subgraph Variance

no code implementations6 Oct 2021 Taige Zhao, XiangYu Song, JianXin Li, Wei Luo, Imran Razzak

We first propose a graph augmentation-based partition (GAD-Partition) that can divide original graph into augmented subgraphs to reduce communication by selecting and storing as few significant nodes of other processors as possible while guaranteeing the accuracy of the training.

Distributed Optimization

Product-oriented Machine Translation with Cross-modal Cross-lingual Pre-training

1 code implementation25 Aug 2021 Yuqing Song, ShiZhe Chen, Qin Jin, Wei Luo, Jun Xie, Fei Huang

Firstly, there are many specialized jargons in the product description, which are ambiguous to translate without the product image.

Machine Translation Translation

About lifespan and the continuous dependence for the Navier-Stokes equation in $\dot{B}^{\frac{d}{p}-1}_{p,r}$

no code implementations24 Dec 2020 Weikui Ye, Zhaoyang Yin, Wei Luo

Combining \cite{wbx, ns7, ns2}, we deduce that $\dot{B}^{\frac{d}{p}-1}_{p,\infty}$ with $1\leq p<\infty$ is the critical space which solutions are ill-posedness, while $u\in\dot{B}^{\frac{d}{p}-1}_{p, r}$ with $1\leq r, p<\infty$ are well-poseness.

Analysis of PDEs

MODEL: Motif-based Deep Feature Learning for Link Prediction

no code implementations9 Aug 2020 Lei Wang, Jing Ren, Bo Xu, Jian-Xin Li, Wei Luo, Feng Xia

Link prediction plays an important role in network analysis and applications.

Link Prediction

Cross-X Learning for Fine-Grained Visual Categorization

no code implementations ICCV 2019 Wei Luo, Xitong Yang, Xianjie Mo, Yuheng Lu, Larry S. Davis, Jun Li, Jian Yang, Ser-Nam Lim

Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.

Ranked #19 on Fine-Grained Image Classification on NABirds (using extra training data)

Fine-Grained Image Classification Fine-Grained Visual Categorization

Aligning Linguistic Words and Visual Semantic Units for Image Captioning

1 code implementation6 Aug 2019 Longteng Guo, Jing Liu, Jinhui Tang, Jiangwei Li, Wei Luo, Hanqing Lu

Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper.

Attribute Image Captioning +2

Learning Longer-term Dependencies via Grouped Distributor Unit

no code implementations29 Apr 2019 Wei Luo, Feng Yu

Learning long-term dependencies still remains difficult for recurrent neural networks (RNNs) despite their success in sequence modeling recently.

Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors

no code implementations1 May 2017 Wei Luo, Lingzhou Xue, Jiawei Yao, Xiufan Yu

Assuming that the predictors affect the response through the latent factors, we propose to first conduct factor analysis and then apply sufficient dimension reduction on the estimated factors, to derive the reduced data for subsequent forecasting.

Dimensionality Reduction Model Selection +3

Control Matching via Discharge Code Sequences

no code implementations2 Dec 2016 Dang Nguyen, Wei Luo, Dinh Phung, Svetha Venkatesh

In this paper, we consider the patient similarity matching problem over a cancer cohort of more than 220, 000 patients.

adaptive direction information in differential evolution for numerical optimization

no code implementations2 Feb 2016 Yiqiao Cai, Jiahai Wang, Yonghong Chen, Tian Wang, Hui Tian, Wei Luo

In most of the DE algorithms, the neighborhood and direction information are not fully and simultaneously exploited to guide the search.

Unsupervised Pretraining Encourages Moderate-Sparseness

no code implementations20 Dec 2013 Jun Li, Wei Luo, Jian Yang, Xiao-Tong Yuan

It is well known that direct training of deep neural networks will generally lead to poor results.

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