Search Results for author: wei he

Found 59 papers, 25 papers with code

Identifying every building's function in large-scale urban areas with multi-modality remote-sensing data

1 code implementation8 May 2024 Zhuohong Li, wei he, Jiepan Li, Hongyan zhang

In this study, we proposed a semi-supervised framework to identify every building's function in large-scale urban areas with multi-modality remote-sensing data.

Self-Demos: Eliciting Out-of-Demonstration Generalizability in Large Language Models

1 code implementation1 Apr 2024 wei he, Shichun Liu, Jun Zhao, Yiwen Ding, Yi Lu, Zhiheng Xi, Tao Gui, Qi Zhang, Xuanjing Huang

The generated demos strategically interpolate between existing demos and the given query, transforming the query from OOD to ID.

In-Context Learning Math

Learning without Exact Guidance: Updating Large-scale High-resolution Land Cover Maps from Low-resolution Historical Labels

3 code implementations5 Mar 2024 Zhuohong Li, wei he, Jiepan Li, Fangxiao Lu, Hongyan zhang

However, it is still a non-trivial task hindered by complex ground details, various landforms, and the scarcity of accurate training labels over a wide-span geographic area.

Pseudo Label Weakly supervised Semantic Segmentation +1

Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models

no code implementations29 Feb 2024 Yu Zhang, long wen, Xiangtong Yao, Zhenshan Bing, Linghuan Kong, wei he, Alois Knoll

Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model's online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from new samples, in conjunction with the learned hyperparameters.

Computational Efficiency Gaussian Processes

DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models

1 code implementation26 Feb 2024 wei he, Kai Han, Yehui Tang, Chengcheng Wang, Yujie Yang, Tianyu Guo, Yunhe Wang

Large language models (LLMs) face a daunting challenge due to the excessive computational and memory requirements of the commonly used Transformer architecture.

Online Efficient Safety-Critical Control for Mobile Robots in Unknown Dynamic Multi-Obstacle Environments

no code implementations26 Feb 2024 Yu Zhang, Guangyao Tian, long wen, Xiangtong Yao, Liding Zhang, Zhenshan Bing, wei he, Alois Knoll

This paper proposes a LiDAR-based goal-seeking and exploration framework, addressing the efficiency of online obstacle avoidance in unstructured environments populated with static and moving obstacles.

LongAgent: Scaling Language Models to 128k Context through Multi-Agent Collaboration

1 code implementation18 Feb 2024 Jun Zhao, Can Zu, Hao Xu, Yi Lu, wei he, Yiwen Ding, Tao Gui, Qi Zhang, Xuanjing Huang

Large language models (LLMs) have demonstrated impressive performance in understanding language and executing complex reasoning tasks.

Multi-hop Question Answering Question Answering +1

LongHeads: Multi-Head Attention is Secretly a Long Context Processor

1 code implementation16 Feb 2024 Yi Lu, Xin Zhou, wei he, Jun Zhao, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

Instead of allowing each head to attend to the full sentence, which struggles with generalizing to longer sequences due to out-of-distribution (OOD) issues, we allow each head to process in-distribution length by selecting and attending to important context chunks.


Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning

1 code implementation8 Feb 2024 Zhiheng Xi, Wenxiang Chen, Boyang Hong, Senjie Jin, Rui Zheng, wei he, Yiwen Ding, Shichun Liu, Xin Guo, Junzhe Wang, Honglin Guo, Wei Shen, Xiaoran Fan, Yuhao Zhou, Shihan Dou, Xiao Wang, Xinbo Zhang, Peng Sun, Tao Gui, Qi Zhang, Xuanjing Huang

In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.

GSM8K reinforcement-learning +1

Adaptive Regularized Low-Rank Tensor Decomposition for Hyperspectral Image Denoising and Destriping

no code implementations11 Jan 2024 Dongyi Li, Dong Chu, Xiaobin Guan, wei he, Huanfeng Shen

On the one hand, the stripe noise is separately modeled by the tensor decomposition, which can effectively encode the spatial-spectral correlation of the stripe noise.

Hyperspectral Image Denoising Image Denoising +1

LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models

no code implementations1 Dec 2023 Ying Nie, wei he, Kai Han, Yehui Tang, Tianyu Guo, Fanyi Du, Yunhe Wang

Moreover, based on the observation that the accuracy of CLIP model does not increase correspondingly as the parameters of text encoder increase, an extra objective of masked language modeling (MLM) is leveraged for maximizing the potential of the shortened text encoder.

Image Classification Language Modelling +3

Cross-level Attention with Overlapped Windows for Camouflaged Object Detection

no code implementations28 Nov 2023 Jiepan Li, Fangxiao Lu, Nan Xue, Zhuohong Li, Hongyan zhang, wei he

In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features.

object-detection Object Detection

A New Adaptive Phase-locked Loop for Synchronization of a Grid-Connected Voltage Source Converter: Simulation and Experimental Results

no code implementations15 Sep 2023 wei he, Jiachen Yan, Romeo Ortega, Daniele Zonetti, Wangping Zhou

In [1] a new adaptive phase-locked loop scheme for synchronization of a grid connected voltage source converter with guaranteed (almost) global stability properties was reported.

Building Extraction from Remote Sensing Images via an Uncertainty-Aware Network

1 code implementation23 Jul 2023 wei he, Jiepan Li, Weinan Cao, Liangpei Zhang, Hongyan zhang

Building extraction aims to segment building pixels from remote sensing images and plays an essential role in many applications, such as city planning and urban dynamic monitoring.

Decoder Extracting Buildings In Remote Sensing Images +1

National-scale 1-m resolution land-cover mapping for the entire China based on a low-cost solution and open-access data

no code implementations9 Mar 2023 Zhuohong Li, wei he, Hongyan zhang

With the rapid urbanization of China, there is an urgent need for creating a very-high-resolution (VHR) national-scale LC map for China.

Towards Complex Backgrounds: A Unified Difference-Aware Decoder for Binary Segmentation

1 code implementation27 Oct 2022 Jiepan Li, wei he, Hongyan zhang

In Stage A, the first branch decoder of the difference-aware decoder is used to obtain a guide map.


Learning by Consuming: Optimal Pricing with Endogenous Information Provision

no code implementations3 Sep 2022 Huiyi Guo, wei he, Bin Liu

We study the revenue-maximizing mechanism when a buyer's value evolves endogenously because of learning-by-consuming.

The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network

no code implementations16 Jul 2022 Zhongzhan Huang, Senwei Liang, Mingfu Liang, wei he, Haizhao Yang, Liang Lin

Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs).

Crowd Counting

Enhancing Sequential Recommendation with Graph Contrastive Learning

no code implementations30 May 2022 Yixin Zhang, Yong liu, Yonghui Xu, Hao Xiong, Chenyi Lei, wei he, Lizhen Cui, Chunyan Miao

Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data.

Auxiliary Learning Contrastive Learning +1

BMD: A General Class-balanced Multicentric Dynamic Prototype Strategy for Source-free Domain Adaptation

1 code implementation6 Apr 2022 Sanqing Qu, Guang Chen, Jing Zhang, Zhijun Li, wei he, DaCheng Tao

Source-free Domain Adaptation (SFDA) aims to adapt a pre-trained source model to the unlabeled target domain without accessing the well-labeled source data, which is a much more practical setting due to the data privacy, security, and transmission issues.

Clustering Pseudo Label +1

Uncovering the dynamic effects of DEX treatment on lung cancer by integrating bioinformatic inference and multiscale modeling of scRNA-seq and proteomics data

no code implementations1 Mar 2022 Minghan Chen, Chunrui Xu, Ziang Xu, wei he, Haorui Zhang, Jing Su, Qianqian Song

Those genes involved in the TGF-\b{eta} pathway and their crosstalk with the ERBB pathway presented a strong survival prognosis in clinical lung cancer samples.

Time Series Analysis

AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training

no code implementations13 Jul 2021 Zhongzhan Huang, Mingfu Liang, Senwei Liang, wei he

Deep neural networks suffer from catastrophic forgetting when learning multiple knowledge sequentially, and a growing number of approaches have been proposed to mitigate this problem.

Continual Learning Semantic Segmentation

Blending Pruning Criteria for Convolutional Neural Networks

no code implementations11 Jul 2021 wei he, Zhongzhan Huang, Mingfu Liang, Senwei Liang, Haizhao Yang

One filter could be important according to a certain criterion, while it is unnecessary according to another one, which indicates that each criterion is only a partial view of the comprehensive "importance".

Clustering Network Pruning

Characterization of equilibrium existence and purification in general Bayesian games

no code implementations16 Jun 2021 wei he, Xiang Sun, Yeneng Sun, Yishu Zeng

This paper studies Bayesian games with general action spaces, correlated types and interdependent payoffs.

From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search

no code implementations24 Mar 2021 Rui Li, Yunjiang Jiang, WenYun Yang, Guoyu Tang, Songlin Wang, Chaoyi Ma, wei he, Xi Xiong, Yun Xiao, Eric Yihong Zhao

We introduce deep learning models to the two most important stages in product search at JD. com, one of the largest e-commerce platforms in the world.

Re-Ranking Retrieval +1

Interpretable Hyperspectral AI: When Non-Convex Modeling meets Hyperspectral Remote Sensing

no code implementations2 Mar 2021 Danfeng Hong, wei he, Naoto Yokoya, Jing Yao, Lianru Gao, Liangpei Zhang, Jocelyn Chanussot, Xiao Xiang Zhu

Hyperspectral imaging, also known as image spectrometry, is a landmark technique in geoscience and remote sensing (RS).

CAP: Context-Aware Pruning for Semantic-Segmentation

1 code implementation6 Jan 2021 wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

In this paper, we advocate the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework.

Network Pruning Segmentation +1


1 code implementation6 Jan 2021 wei he, Meiqing Wu, Mingfu Liang, Siew-Kei Lam

In this paper, we advocate the importance of contextual information during channel pruning for semantic segmentation networks by presenting a novel Context-aware Pruning framework.

Network Pruning Segmentation +1

Improving robustness of softmax corss-entropy loss via inference information

no code implementations1 Jan 2021 Bingbing Song, wei he, Renyang Liu, Shui Yu, Ruxin Wang, Mingming Gong, Tongliang Liu, Wei Zhou

Several state-of-the-arts start from improving the inter-class separability of training samples by modifying loss functions, where we argue that the adversarial samples are ignored and thus limited robustness to adversarial attacks is resulted.

Fast Hyperspectral Image Recovery via Non-iterative Fusion of Dual-Camera Compressive Hyperspectral Imaging

no code implementations30 Dec 2020 wei he, Naoto Yokoya, Xin Yuan

Specifically, the RGB measurement is utilized to estimate the coefficients, meanwhile the CASSI measurement is adopted to provide the orthogonal spectral basis.

Site-Specific Structure at Multiple Length Scales in Kagome Quantum Spin Liquid Candidates

no code implementations14 Dec 2020 Rebecca W. Smaha, Idris Boukahil, Charles J. Titus, Jack Mingde Jiang, John P. Sheckelton, wei he, Jiajia Wen, John Vinson, Suyin Grass Wang, Yu-Sheng Chen, Simon J. Teat, Thomas P. Devereaux, C. Das Pemmaraju, Young S. Lee

Realizing a quantum spin liquid (QSL) ground state in a real material is a leading issue in condensed matter physics research.

Strongly Correlated Electrons Materials Science

Efficient Attention Network: Accelerate Attention by Searching Where to Plug

1 code implementation28 Nov 2020 Zhongzhan Huang, Senwei Liang, Mingfu Liang, wei he, Haizhao Yang

Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (CNNs).

Unmixing Convolutional Features for Crisp Edge Detection

1 code implementation19 Nov 2020 Linxi Huan, Nan Xue, Xianwei Zheng, wei he, Jianya Gong, Gui-Song Xia

This paper presents a context-aware tracing strategy (CATS) for crisp edge detection with deep edge detectors, based on an observation that the localization ambiguity of deep edge detectors is mainly caused by the mixing phenomenon of convolutional neural networks: feature mixing in edge classification and side mixing during fusing side predictions.

Edge Classification Edge Detection

Nonlinear Cooperative Control of Double Drone-Bar Transportation System

no code implementations15 Nov 2020 Peng Zhang, Yongchun Fang, Xiao Liang, He Lin, wei he

Due to the limitation of the drone's load capacity, various specific tasks need to be accomplished by multiple drones in collaboration.

Dynamical Systems Systems and Control Systems and Control

Non-local Meets Global: An Iterative Paradigm for Hyperspectral Image Restoration

1 code implementation24 Oct 2020 wei he, Quanming Yao, Chao Li, Naoto Yokoya, Qibin Zhao, Hongyan zhang, Liangpei Zhang

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) restoration, which includes the tasks of denoising, compressed HSI reconstruction and inpainting.

Denoising Image Restoration

A Network-Guided Reaction-Diffusion Model of AT[N] Biomarkers in Alzheimer's Disease

no code implementations10 Sep 2020 Jingwen Zhang, Defu Yang, wei he, Guorong Wu, Minghan Chen

Currently, many studies of Alzheimer's disease (AD) are investigating the neurobiological factors behind the acquisition of beta-amyloid (A), pathologic tau (T), and neurodegeneration ([N]) biomarkers from neuroimages.

Guided Deep Decoder: Unsupervised Image Pair Fusion

1 code implementation ECCV 2020 Tatsumi Uezato, Danfeng Hong, Naoto Yokoya, wei he

The proposed network is composed of an encoder-decoder network that exploits multi-scale features of a guidance image and a deep decoder network that generates an output image.

Decoder Pansharpening

Illumination invariant hyperspectral image unmixing based on a digital surface model

no code implementations23 Jul 2020 Tatsumi Uezato, Naoto Yokoya, wei he

Although many spectral unmixing models have been developed to address spectral variability caused by variable incident illuminations, the mechanism of the spectral variability is still unclear.

Breaking the Limits of Remote Sensing by Simulation and Deep Learning for Flood and Debris Flow Mapping

1 code implementation9 Jun 2020 Naoto Yokoya, Kazuki Yamanoi, wei he, Gerald Baier, Bruno Adriano, Hiroyuki Miura, Satoru Oishi

We propose a framework that estimates inundation depth (maximum water level) and debris-flow-induced topographic deformation from remote sensing imagery by integrating deep learning and numerical simulation.

Change Detection

Hyperspectral Super-Resolution via Coupled Tensor Ring Factorization

no code implementations6 Jan 2020 Wei He, Yong Chen, Naoto Yokoya, Chao Li, Qibin Zhao

In this paper, we propose a new model, named coupled tensor ring factorization (CTRF), for HSR.


Answer-focused and Position-aware Neural Question Generation

no code implementations EMNLP 2018 Xingwu Sun, Jing Liu, Yajuan Lyu, wei he, Yanjun Ma, Shi Wang

(2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer.

Machine Reading Comprehension Position +3

Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes

no code implementations30 Jul 2018 Xianyan Jia, Shutao Song, wei he, Yangzihao Wang, Haidong Rong, Feihu Zhou, Liqiang Xie, Zhenyu Guo, Yuanzhou Yang, Liwei Yu, Tiegang Chen, Guangxiao Hu, Shaohuai Shi, Xiaowen Chu

(3) We propose highly optimized all-reduce algorithms that achieve up to 3x and 11x speedup on AlexNet and ResNet-50 respectively than NCCL-based training on a cluster with 1024 Tesla P40 GPUs.

Playing the Game of 2048

Multi-temporal Sentinel-1 and -2 Data Fusion for Optical Image Simulation

no code implementations26 Jul 2018 Wei He, Naoto Yokoya

In this paper, we present the optical image simulation from a synthetic aperture radar (SAR) data using deep learning based methods.

Cloud Removal Generative Adversarial Network

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

no code implementations ACL 2018 Yizhong Wang, Kai Liu, Jing Liu, wei he, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine.

Machine Reading Comprehension Question Answering

A New Method of Region Embedding for Text Classification

1 code implementation ICLR 2018 chao qiao, Bo Huang, guocheng niu, daren li, daxiang dong, wei he, dianhai yu, Hua Wu

In this paper, we propose a new method of learning and utilizing task-specific distributed representations of n-grams, referred to as “region embeddings”.

General Classification text-classification +1

DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications

3 code implementations WS 2018 Wei He, Kai Liu, Jing Liu, Yajuan Lyu, Shiqi Zhao, Xinyan Xiao, Yu-An Liu, Yizhong Wang, Hua Wu, Qiaoqiao She, Xuan Liu, Tian Wu, Haifeng Wang

Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.

Machine Reading Comprehension

Semi-Supervised Learning for Neural Machine Translation

no code implementations ACL 2016 Yong Cheng, Wei Xu, Zhongjun He, wei he, Hua Wu, Maosong Sun, Yang Liu

While end-to-end neural machine translation (NMT) has made remarkable progress recently, NMT systems only rely on parallel corpora for parameter estimation.

Decoder Machine Translation +2

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