Search Results for author: Xiaofeng Zhang

Found 39 papers, 12 papers with code

Building the Directed Semantic Graph for Coherent Long Text Generation

no code implementations EMNLP 2021 Ziao Wang, Xiaofeng Zhang, Hongwei Du

These directed subgraphs are considered to well preserve extra but relevant content to the short input text, and then they are decoded by the employed pre-trained model to generate coherent long text.

Sentence Sentence Embedding +2

From Redundancy to Relevance: Enhancing Explainability in Multimodal Large Language Models

no code implementations4 Jun 2024 Xiaofeng Zhang, Chen Shen, Xiaosong Yuan, Shaotian Yan, Liang Xie, Wenxiao Wang, Chaochen Gu, Hao Tang, Jieping Ye

To explore the interaction process between image and text in complex reasoning tasks, we introduce the information flow method to visualize the interaction mechanism.

Language Modelling Large Language Model

Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement

1 code implementation6 May 2024 Jiesong Bai, Yuhao Yin, Qiyuan He, Yuanxian Li, Xiaofeng Zhang

In the field of low-light image enhancement, both traditional Retinex methods and advanced deep learning techniques such as Retinexformer have shown distinct advantages and limitations.

Computational Efficiency Low-Light Image Enhancement +1

Building Lane-Level Maps from Aerial Images

1 code implementation20 Dec 2023 Jiawei Yao, Xiaochao Pan, Tong Wu, Xiaofeng Zhang

In this paper, we introduce for the first time a large-scale aerial image dataset built for lane detection, with high-quality polyline lane annotations on high-resolution images of around 80 kilometers of road.

Autonomous Driving Lane Detection

Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement

no code implementations15 Dec 2023 Xiaofeng Zhang, Zishan Xu, Hao Tang, Chaochen Gu, Wei Chen, Shanying Zhu, Xinping Guan

Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results.

Low-Light Image Enhancement

Efficient Remote Sensing Segmentation With Generative Adversarial Transformer

no code implementations2 Oct 2023 Luyi Qiu, Dayu Yu, Xiaofeng Zhang, Chenxiao Zhang

Most deep learning methods that achieve high segmentation accuracy require deep network architectures that are too heavy and complex to run on embedded devices with limited storage and memory space.

Segmentation Semantic Segmentation

Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis

no code implementations18 Sep 2023 Tianyi Song, Jiuxin Cao, Kun Wang, Bo Liu, Xiaofeng Zhang

The current state-of-the-art method combines the features of historical captions, historical frames, and the current captions as conditions for generating the current frame.

Image Generation Story Generation

Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN

no code implementations16 Aug 2023 Jiawei Yao, Tong Wu, Xiaofeng Zhang

To explore the differences between Transformers and CNNs, we employ a sparse pixel approach to contrastively analyze the distinctions between the two.

Monocular Depth Estimation

An Effective Data Creation Pipeline to Generate High-quality Financial Instruction Data for Large Language Model

no code implementations31 Jul 2023 Ziao Wang, Jianning Wang, Junda Wu, Xiaofeng Zhang

At the beginning era of large language model, it is quite critical to generate a high-quality financial dataset to fine-tune a large language model for financial related tasks.

Language Modelling Large Language Model

FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis

1 code implementation31 Jul 2023 Ziao Wang, Yuhang Li, Junda Wu, Jaehyeon Soon, Xiaofeng Zhang

In this paper, we propose FinVis-GPT, a novel multimodal large language model (LLM) specifically designed for financial chart analysis.

Language Modelling Large Language Model

Weakly supervised learning for pattern classification in serial femtosecond crystallography

no code implementations30 Jul 2023 Jianan Xie, Ji Liu, Chi Zhang, Xihui Chen, Ping Huai, Jie Zheng, Xiaofeng Zhang

Th is heavy dependence on labeled datasets will seriously restrict the application of networks, because it is very costly to annotate a large number of diffraction patterns.

Weakly-supervised Learning

BrickPal: Augmented Reality-based Assembly Instructions for Brick Models

no code implementations6 Jul 2023 Yao Shi, Xiaofeng Zhang, Ran Zhang, Zhou Yang, Xiao Tang, Hongni Ye, Yi Wu

The assembly instruction is a mandatory component of Lego-like brick sets. The conventional production of assembly instructions requires a considerable amount of manual fine-tuning, which is intractable for casual users and customized brick sets. Moreover, the traditional paper-based instructions lack expressiveness and interactivity. To tackle the two problems above, we present BrickPal, an augmented reality-based system, which visualizes assembly instructions in an augmented reality head-mounted display.

Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement

2 code implementations17 Jun 2023 Qihan Zhao, Xiaofeng Zhang, Hao Tang, Chaochen Gu, Shanying Zhu

Image restoration is a low-level visual task, and most CNN methods are designed as black boxes, lacking transparency and intrinsic aesthetics.

Image Restoration Low-Light Image Enhancement +2

Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing

no code implementations5 Jun 2023 Biao Wu, Shaoli Liu, Diankai Zhang, Chengjian Zheng, Si Gao, Xiaofeng Zhang, Ning Wang

Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image.

Scene Understanding Semantic Segmentation +1

SAM-helps-Shadow:When Segment Anything Model meet shadow removal

1 code implementation1 Jun 2023 Xiaofeng Zhang, Chaochen Gu, Shanying Zhu

The challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-shot learning in this field.

Image Shadow Removal Shadow Detection And Removal +2

Transformer-Patcher: One Mistake worth One Neuron

1 code implementation24 Jan 2023 Zeyu Huang, Yikang Shen, Xiaofeng Zhang, Jie zhou, Wenge Rong, Zhang Xiong

Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME).

Model Editing

Mixture of Attention Heads: Selecting Attention Heads Per Token

1 code implementation11 Oct 2022 Xiaofeng Zhang, Yikang Shen, Zeyu Huang, Jie zhou, Wenge Rong, Zhang Xiong

This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.

Computational Efficiency Language Modelling +2

GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs

no code implementations12 Aug 2022 Linhao Luo, Yixiang Fang, Moli Lu, Xin Cao, Xiaofeng Zhang, Wenjie Zhang

Most of existing relevance measures focus on homogeneous networks where objects are of the same type, and a few measures are developed for heterogeneous graphs, but they often need the pre-defined meta-path.

Community Detection Graph Mining +2

VDPC: Variational Density Peak Clustering Algorithm

no code implementations29 Dec 2021 Yizhang Wang, Di Wang, You Zhou, Xiaofeng Zhang, Chai Quek

Furthermore, we divide all data points into different levels according to their local density and propose a unified clustering framework by combining the advantages of both DPC and DBSCAN.

Clustering

DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation

no code implementations30 May 2021 Liqi Yang, Linhan Luo, Lifeng Xin, Xiaofeng Zhang, Xinni Zhang

Then, the demand-aware graph neural network is designed to extract session demand graph to learn the demand-aware item embedddings for the later recommendations.

Graph Neural Network Session-Based Recommendations

RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating

no code implementations25 Nov 2020 Linhao Luo, Liqi Yang, Ju Xin, Yixiang Fang, Xiaofeng Zhang, Xiaofei Yang, Kai Chen, Zhiyuan Zhang, Kai Liu

In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.

Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition

no code implementations26 Oct 2020 Gang Wang, Qunxi Dong, Jianfeng Wu, Yi Su, Kewei Chen, Qingtang Su, Xiaofeng Zhang, Jinguang Hao, Tao Yao, Li Liu, Caiming Zhang, Richard J Caselli, Eric M Reiman, Yalin Wang

With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.

Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation

no code implementations23 Oct 2020 Yunpeng Ren, Ziao Wang, Yiyuan Wang, Xiaofeng Zhang

Particularly, we choose Bi-GRU as the encoder and decoder component of CVAE, and learn the latent variable distribution from input news.

Decoder Knowledge Distillation

SiENet: Siamese Expansion Network for Image Extrapolation

1 code implementation8 Jul 2020 Xiaofeng Zhang, Feng Chen, Cailing Wang, Songsong Wu, Ming Tao, Guoping Jiang

In this paper, a novel two-stage siamese adversarial model for image extrapolation, named Siamese Expansion Network (SiENet) is proposed.

Decoder Image Inpainting +1

Automatically Generating Macro Research Reports from a Piece of News

no code implementations21 Nov 2019 Wenxin Hu, Xiaofeng Zhang, Gang Yang

As we all know, it requires the macro analysts to write such reports within a short period of time after the important economic news are released.

Text Generation

Structure Matters: Towards Generating Transferable Adversarial Images

no code implementations22 Oct 2019 Dan Peng, Zizhan Zheng, Linhao Luo, Xiaofeng Zhang

In this paper, we propose the novel concepts of structure patterns and structure-aware perturbations that relax the small perturbation constraint while still keeping images natural.

Image Classification Novel Concepts +1

Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better

no code implementations23 Sep 2019 Yaping Zheng, Shiyi Chen, Xinni Zhang, Xiaofeng Zhang, Xiaofei Yang, Di Wang

Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data.

Community Detection

Wasserstein Autoencoders for Collaborative Filtering

no code implementations15 Sep 2018 Jingbin Zhong, Xiaofeng Zhang

Two different cost functions are designed for measuring the distance between the implicit feedback data and its re-generated version of data.

Collaborative Filtering Recommendation Systems

Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples

1 code implementation8 Sep 2018 Dan Peng, Zizhan Zheng, Xiaofeng Zhang

A common requirement in all these works is that the malicious perturbations should be small enough (measured by an L_p norm for some p) so that they are imperceptible to humans.

Image Classification

DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification

2 code implementations29 Aug 2018 Xiaofeng Zhang, Zhangyang Wang, Dong Liu, Qing Ling

Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else.

Data Augmentation General Classification +2

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