Search Results for author: Zhenwei Shi

Found 74 papers, 42 papers with code

MFogHub: Bridging Multi-Regional and Multi-Satellite Data for Global Marine Fog Detection and Forecasting

1 code implementation15 May 2025 Mengqiu Xu, Kaixin Chen, Heng Guo, Yixiang Huang, Ming Wu, Zhenwei Shi, Chuang Zhang, Jun Guo

Deep learning approaches for marine fog detection and forecasting have outperformed traditional methods, demonstrating significant scientific and practical importance.

BlockGaussian: Efficient Large-Scale Scene Novel View Synthesis via Adaptive Block-Based Gaussian Splatting

1 code implementation12 Apr 2025 Yongchang Wu, Zipeng Qi, Zhenwei Shi, Zhengxia Zou

This paper introduces BlockGaussian, a novel framework incorporating a content-aware scene partition strategy and visibility-aware block optimization to achieve efficient and high-quality large-scale scene reconstruction.

3DGS Novel View Synthesis

Towards Computation- and Communication-efficient Computational Pathology

no code implementations3 Apr 2025 Chu Han, Bingchao Zhao, Jiatai Lin, Shanshan Lyu, Longfei Wang, Tianpeng Deng, Cheng Lu, Changhong Liang, Hannah Y. Wen, Xiaojing Guo, Zhenwei Shi, Zaiyi Liu

Despite the impressive performance across a wide range of applications, current computational pathology models face significant diagnostic efficiency challenges due to their reliance on high-magnification whole-slide image analysis.

Diagnostic Self-Supervised Learning

DynamicVis: An Efficient and General Visual Foundation Model for Remote Sensing Image Understanding

1 code implementation20 Mar 2025 Keyan Chen, Chenyang Liu, Bowen Chen, Wenyuan Li, Zhengxia Zou, Zhenwei Shi

Motivated by the selective attention mechanisms inherent to the human visual system, we propose DynamicVis, a dynamic visual perception foundation model for remote sensing imagery.

Heterogeneous Mixture of Experts for Remote Sensing Image Super-Resolution

1 code implementation12 Feb 2025 Bowen Chen, Keyan Chen, Mohan Yang, Zhengxia Zou, Zhenwei Shi

To address this issue, we introduce a Mixture of Experts (MoE) model and design a set of heterogeneous experts.

Image Super-Resolution Mixture-of-Experts

Kolmogorov Arnold Neural Interpolator for Downscaling and Correcting Meteorological Fields from In-Situ Observations

no code implementations24 Jan 2025 Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Zhengxia Zou, Zhenwei Shi

Obtaining accurate weather forecasts at station locations is a critical challenge due to systematic biases arising from the mismatch between multi-scale, continuous atmospheric characteristic and their discrete, gridded representations.

WSSM: Geographic-enhanced hierarchical state-space model for global station weather forecast

no code implementations20 Jan 2025 Songru Yang, Zili Liu, Zhenwei Shi, Zhengxia Zou

Global Station Weather Forecasting (GSWF), a prominent meteorological research area, is pivotal in providing timely localized weather predictions.

Mamba State Space Models +1

Semantic-CD: Remote Sensing Image Semantic Change Detection towards Open-vocabulary Setting

no code implementations12 Jan 2025 Yongshuo Zhu, Lu Li, Keyan Chen, Chenyang Liu, Fugen Zhou, Zhenwei Shi

To address this issue, we introduce a novel approach called Semantic-CD, specifically designed for semantic change detection in remote sensing images.

Change Detection Decoder +1

RSRefSeg: Referring Remote Sensing Image Segmentation with Foundation Models

1 code implementation12 Jan 2025 Keyan Chen, Jiafan Zhang, Chenyang Liu, Zhengxia Zou, Zhenwei Shi

Referring remote sensing image segmentation is crucial for achieving fine-grained visual understanding through free-format textual input, enabling enhanced scene and object extraction in remote sensing applications.

Image Segmentation Segmentation +1

Text2Earth: Unlocking Text-driven Remote Sensing Image Generation with a Global-Scale Dataset and a Foundation Model

no code implementations1 Jan 2025 Chenyang Liu, Keyan Chen, Rui Zhao, Zhengxia Zou, Zhenwei Shi

On the previous benchmark dataset, Text2Earth outperforms previous models with an improvement of +26. 23 FID and +20. 95% Zero-shot Cls-OA metric. Our project page is \url{https://chen-yang-liu. github. io/Text2Earth}

Image Generation

Efficient Semantic Splatting for Remote Sensing Multi-view Segmentation

no code implementations8 Dec 2024 Zipeng Qi, Hao Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi

In this paper, we propose a novel semantic splatting approach based on Gaussian Splatting to achieve efficient and low-latency.

Semantic Segmentation

Remote Sensing Temporal Vision-Language Models: A Comprehensive Survey

1 code implementation3 Dec 2024 Chenyang Liu, Jiafan Zhang, Keyan Chen, Man Wang, Zhengxia Zou, Zhenwei Shi

This survey fills a critical gap in the literature by providing an integrated overview of RSTVLM, offering a foundation for further advancements in remote sensing temporal image understanding.

Change Detection Descriptive +4

Joint-Optimized Unsupervised Adversarial Domain Adaptation in Remote Sensing Segmentation with Prompted Foundation Model

1 code implementation8 Nov 2024 Shuchang Lyu, Qi Zhao, Guangliang Cheng, Yiwei He, Zheng Zhou, Guangbiao Wang, Zhenwei Shi

This task presents two principal challenges: (1) severe inconsistencies in feature representation across different remote sensing domains, and (2) a domain gap that emerges due to the representation bias of source domain patterns when translating features to predictive logits.

Decoder Semantic Segmentation +1

Sitcom-Crafter: A Plot-Driven Human Motion Generation System in 3D Scenes

1 code implementation14 Oct 2024 Jianqi Chen, Panwen Hu, Xiaojun Chang, Zhenwei Shi, Michael Christian Kampffmeyer, Xiaodan Liang

Recent advancements in human motion synthesis have focused on specific types of motions, such as human-scene interaction, locomotion or human-human interaction, however, there is a lack of a unified system capable of generating a diverse combination of motion types.

Motion Generation Motion Synthesis +1

Exploring Fine-Grained Image-Text Alignment for Referring Remote Sensing Image Segmentation

1 code implementation20 Sep 2024 Sen Lei, Xinyu Xiao, Tianlin Zhang, Heng-Chao Li, Zhenwei Shi, Qing Zhu

Given a language expression, referring remote sensing image segmentation (RRSIS) aims to identify ground objects and assign pixel-wise labels within the imagery.

Image Segmentation Referring Expression +1

Adapt CLIP as Aggregation Instructor for Image Dehazing

no code implementations22 Aug 2024 Xiaozhe Zhang, Fengying Xie, Haidong Ding, Linpeng Pan, Zhenwei Shi

Most dehazing methods suffer from limited receptive field and do not explore the rich semantic prior encapsulated in vision-language models, which have proven effective in downstream tasks.

Image Dehazing Mamba

MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling

no code implementations20 Aug 2024 Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi

In an era of frequent extreme weather and global warming, obtaining precise, fine-grained near-surface weather forecasts is increasingly essential for human activities.

Mamba Super-Resolution

Open-CD: A Comprehensive Toolbox for Change Detection

1 code implementation22 Jul 2024 Kaiyu Li, Jiawei Jiang, Andrea Codegoni, Chengxi Han, Yupeng Deng, Keyan Chen, Zhuo Zheng, Hao Chen, Zhengxia Zou, Zhenwei Shi, Sheng Fang, Deyu Meng, Zhi Wang, Xiangyong Cao

We present Open-CD, a change detection toolbox that contains a rich set of change detection methods as well as related components and modules.

Benchmarking Change Detection

Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling

1 code implementation22 Jul 2024 Bo Yuan, Danpei Zhao, Zhenwei Shi

Concretely, the proposed decoupling manner includes two ways, i. e., channel-wise decoupling and spatial-level neuron-relevant semantic consistency.

Continual Semantic Segmentation Contrastive Learning +2

Semantic-CC: Boosting Remote Sensing Image Change Captioning via Foundational Knowledge and Semantic Guidance

no code implementations19 Jul 2024 Yongshuo Zhu, Lu Li, Keyan Chen, Chenyang Liu, Fugen Zhou, Zhenwei Shi

Remote sensing image change captioning (RSICC) aims to articulate the changes in objects of interest within bi-temporal remote sensing images using natural language.

Change Detection Decoder +2

Transformer for Multitemporal Hyperspectral Image Unmixing

no code implementations15 Jul 2024 Hang Li, Qiankun Dong, Xueshuo Xie, Xia Xu, Tao Li, Zhenwei Shi

To effectively perform multitemporal hyperspectral image unmixing, we introduce two key modules: the Global Awareness Module (GAM) and the Change Enhancement Module (CEM).

C$^3$DG: Conditional Domain Generalization for Hyperspectral Imagery Classification with Convergence and Constrained-risk Theories

no code implementations4 Jul 2024 Zhe Gao, Bin Pan, Zhenwei Shi

In this paper, we only rely on spectral information to solve the hyperspectral-monospectra problem, and propose a Convergence and Error-Constrained Conditional Domain Generalization method for Hyperspectral Imagery Classification (C$^3$DG).

Domain Generalization

A Late-Stage Bitemporal Feature Fusion Network for Semantic Change Detection

1 code implementation15 Jun 2024 Chenyao Zhou, Haotian Zhang, Han Guo, Zhengxia Zou, Zhenwei Shi

Recently some multi-task learning based semantic change detection methods have been proposed to decompose the task into semantic segmentation and binary change detection subtasks.

Change Detection Earth Observation +2

Domain Agnostic Conditional Invariant Predictions for Domain Generalization

no code implementations9 Jun 2024 Zongbin Wang, Bin Pan, Zhenwei Shi

In DRM theory, we prove that reducing the discrepancy of prediction distribution between overall source domain and any subset of it can contribute to obtaining invariant features.

Bayesian Inference Domain Generalization

Domain Generalization Guided by Large-Scale Pre-Trained Priors

no code implementations9 Jun 2024 Zongbin Wang, Bin Pan, Shiyu Shen, Tianyang Shi, Zhenwei Shi

In summary, we offer a new fine-tuning method for DG algorithms to utilize pre-trained models throughout the fine-tuning process.

Domain Generalization

CDMamba: Remote Sensing Image Change Detection with Mamba

3 code implementations6 Jun 2024 Haotian Zhang, Keyan Chen, Chenyang Liu, Hao Chen, Zhengxia Zou, Zhenwei Shi

Specifically, the Scaled Residual ConvMamba (SRCM) block is proposed to utilize the ability of Mamba to extract global features and convolution to enhance the local details, to alleviate the issue that current Mamba-based methods lack detailed clues and are difficult to achieve fine detection in dense prediction tasks.

Change Detection Mamba +1

MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation

no code implementations22 May 2024 Zhiping Yu, Chenyang Liu, Liqin Liu, Zhenwei Shi, Zhengxia Zou

To achieve unbounded and arbitrary-sized image generation, we design a novel noise sampling strategy for denoising diffusion models by analyzing the generation conditions and initial noise.

Denoising Image Generation

RSCaMa: Remote Sensing Image Change Captioning with State Space Model

1 code implementation29 Apr 2024 Chenyang Liu, Keyan Chen, Bowen Chen, Haotian Zhang, Zhengxia Zou, Zhenwei Shi

In terms of efficient temporal modeling, considering the potential correlation between the temporal scanning characteristics of Mamba and the temporality of the RSICC, we propose the Temporal-Traversing SSM (TT-SSM), which scans bi-temporal features in a temporal cross-wise manner, enhancing the model's temporal understanding and information interaction.

Decoder Mamba

MarsSeg: Mars Surface Semantic Segmentation with Multi-level Extractor and Connector

no code implementations5 Apr 2024 Junbo Li, Keyan Chen, Gengju Tian, Lu Li, Zhenwei Shi

The Mini-ASPP and PSA are specifically designed for shadow feature enhancement, thereby enabling the expression of local details and small objects.

Decoder Segmentation +2

Change-Agent: Towards Interactive Comprehensive Remote Sensing Change Interpretation and Analysis

1 code implementation28 Mar 2024 Chenyang Liu, Keyan Chen, Haotian Zhang, Zipeng Qi, Zhengxia Zou, Zhenwei Shi

Remote sensing satellite imagery offers a unique perspective for monitoring these changes, leading to the emergence of remote sensing image change interpretation (RSICI) as a significant research focus.

Change Detection Language Modelling +2

RSMamba: Remote Sensing Image Classification with State Space Model

3 code implementations28 Mar 2024 Keyan Chen, Bowen Chen, Chenyang Liu, Wenyuan Li, Zhengxia Zou, Zhenwei Shi

Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation.

Classification Image Classification +3

BiFA: Remote Sensing Image Change Detection With Bitemporal Feature Alignment

1 code implementation IEEE Transactions on Geoscience and Remote Sensing 2024 Haotian Zhang, Hao Chen, Chenyao Zhou, Keyan Chen, Chenyang Liu, Zhengxia Zou, Zhenwei Shi

Despite the success of deep learning-based change detection (CD) methods, their existing insufficiency in temporal (channel and spatial) and multiscale alignment has rendered them insufficient capability in mitigating external factors (illumination changes and perspective differences) arising from different imaging conditions during CD.

Change Detection

Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method

1 code implementation22 Jan 2024 Zili Liu, Hao Chen, Lei Bai, Wenyuan Li, Keyan Chen, Zhengyi Wang, Wanli Ouyang, Zhengxia Zou, Zhenwei Shi

In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field.

Super-Resolution Weather Forecasting

Learning to detect cloud and snow in remote sensing images from noisy labels

no code implementations17 Jan 2024 Zili Liu, Hao Chen, Wenyuan Li, Keyan Chen, Zipeng Qi, Chenyang Liu, Zhengxia Zou, Zhenwei Shi

This paper is the first to consider the impact of label noise on the detection of clouds and snow in remote sensing images.

Diversity Semantic Segmentation

DeepPhysiNet: Bridging Deep Learning and Atmospheric Physics for Accurate and Continuous Weather Modeling

1 code implementation4 Jan 2024 Wenyuan Li, Zili Liu, Keyan Chen, Hao Chen, Shunlin Liang, Zhengxia Zou, Zhenwei Shi

Next, we construct hyper-networks based on deep learning methods to directly learn weather patterns from a large amount of meteorological data.

Weather Forecasting

Pixel-Level Change Detection Pseudo-Label Learning for Remote Sensing Change Captioning

no code implementations23 Dec 2023 Chenyang Liu, Keyan Chen, Zipeng Qi, Haotian Zhang, Zhengxia Zou, Zhenwei Shi

The existing methods for Remote Sensing Image Change Captioning (RSICC) perform well in simple scenes but exhibit poorer performance in complex scenes.

Change Detection Pseudo Label

PETDet: Proposal Enhancement for Two-Stage Fine-Grained Object Detection

1 code implementation16 Dec 2023 Wentao Li, Danpei Zhao, Bo Yuan, Yue Gao, Zhenwei Shi

Fine-grained object detection (FGOD) extends object detection with the capability of fine-grained recognition.

Multi-Task Learning Object +3

Bayesian Domain Invariant Learning via Posterior Generalization of Parameter Distributions

no code implementations25 Oct 2023 Shiyu Shen, Bin Pan, Tianyang Shi, Tao Li, Zhenwei Shi

We first propose a theorem to show that the invariant posterior of parameters can be implicitly inferred by aggregating posteriors on different training domains.

Domain Generalization Variational Inference

Be Bayesian by Attachments to Catch More Uncertainty

no code implementations19 Oct 2023 Shiyu Shen, Bin Pan, Tianyang Shi, Tao Li, Zhenwei Shi

Bayesian Neural Networks (BNNs) have become one of the promising approaches for uncertainty estimation due to the solid theorical foundations.

Zero-Shot Image Harmonization with Generative Model Prior

1 code implementation17 Jul 2023 Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, Zhenwei Shi

Initially, we employ a pretrained vision-language model (VLM) to generate descriptions for the composite image.

Image Harmonization Language Modeling +2

RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model

1 code implementation28 Jun 2023 Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, Zhenwei Shi

We also propose several ongoing derivatives for instance segmentation tasks, drawing on recent advancements within the SAM community, and compare their performance with RSPrompter.

Image Segmentation Instance Segmentation +3

Continuous Cross-resolution Remote Sensing Image Change Detection

1 code implementation24 May 2023 Hao Chen, Haotian Zhang, Keyan Chen, Chenyao Zhou, Song Chen, Zhengxia Zou, Zhenwei Shi

Toward continuous cross-resolution CD, we propose scale-invariant learning to enforce the model consistently predicting HR results given synthesized samples of varying resolution differences.

Change Detection

Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation

no code implementations15 Mar 2023 Zipeng Qi, Hao Chen, Chenyang Liu, Zhenwei Shi, Zhengxia Zou

In the first stage, we optimize a neural field to encode the color and 3D structure of the remote sensing scene based on multi-view images.

Image Segmentation Scene Segmentation +1

Dense Pixel-to-Pixel Harmonization via Continuous Image Representation

1 code implementation3 Mar 2023 Jianqi Chen, Yilan Zhang, Zhengxia Zou, Keyan Chen, Zhenwei Shi

High-resolution (HR) image harmonization is of great significance in real-world applications such as image synthesis and image editing.

Image Harmonization

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation

no code implementations CVPR 2023 Rui Zhao, Wei Li, Zhipeng Hu, Lincheng Li, Zhengxia Zou, Zhenwei Shi, Changjie Fan

In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework.

3D Generation Face Model +3

Progressive Scale-aware Network for Remote sensing Image Change Captioning

1 code implementation1 Mar 2023 Chenyang Liu, Jiajun Yang, Zipeng Qi, Zhengxia Zou, Zhenwei Shi

To sufficiently utilize the extracted multi-scale features for captioning, we propose a scale-aware reinforcement (SR) module and combine it with the Transformer decoding layer to progressively utilize the features from different PDP layers.

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification

1 code implementation24 Feb 2023 Tianpeng Deng, Yanqi Huang, Guoqiang Han, Zhenwei Shi, Jiatai Lin, Qi Dou, Zaiyi Liu, Xiao-jing Guo, C. L. Philip Chen, Chu Han

In this paper, we propose a universal and lightweight federated learning framework, named Federated Deep-Broad Learning (FedDBL), to achieve superior classification performance with limited training samples and only one-round communication.

Federated Learning

Continuous Remote Sensing Image Super-Resolution based on Context Interaction in Implicit Function Space

1 code implementation16 Feb 2023 Keyan Chen, Wenyuan Li, Sen Lei, Jianqi Chen, XiaoLong Jiang, Zhengxia Zou, Zhenwei Shi

Despite its fruitful applications in remote sensing, image super-resolution is troublesome to train and deploy as it handles different resolution magnifications with separate models.

Image Super-Resolution

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

1 code implementation27 May 2022 Hao Chen, Wenyuan Li, Song Chen, Zhenwei Shi

To achieve this, we obtain multiple points via class-balanced sampling on the overlapped area between views using the semantic mask.

Change Detection Representation Learning +2

Remote Sensing Novel View Synthesis with Implicit Multiplane Representations

1 code implementation18 May 2022 Yongchang Wu, Zhengxia Zou, Zhenwei Shi

In this paper, we propose a novel remote sensing view synthesis method by leveraging the recent advances in implicit neural representations.

Novel View Synthesis

Dual-Branched Spatio-temporal Fusion Network for Multi-horizon Tropical Cyclone Track Forecast

no code implementations27 Feb 2022 Zili Liu, Kun Hao, Xiaoyi Geng, Zhenwei Shi

Tropical cyclone (TC) is an extreme tropical weather system and its trajectory can be described by a variety of spatio-temporal data.

Decoder Tropical Cyclone Track Forecasting

Geographical Knowledge-driven Representation Learning for Remote Sensing Images

1 code implementation12 Jul 2021 Wenyuan Li, Keyan Chen, Hao Chen, Zhenwei Shi

The proliferation of remote sensing satellites has resulted in a massive amount of remote sensing images.

object-detection Object Detection +3

Lung Cancer Diagnosis Using Deep Attention Based on Multiple Instance Learning and Radiomics

no code implementations29 Apr 2021 Junhua Chen, Haiyan Zeng, Chong Zhang, Zhenwei Shi, Andre Dekker, Leonard Wee, Inigo Bermejo

In this article, we treat lung cancer diagnosis as a multiple instance learning (MIL) problem in order to better reflect the diagnosis process in the clinical setting and for the higher interpretability of the output.

Deep Attention Lung Cancer Diagnosis +2

Feedback Refined Local-Global Network for Super-Resolution of Hyperspectral Imagery

no code implementations7 Mar 2021 Zhenjie Tang, Qing Xu, Zhenwei Shi, Bin Pan

To be specific, we develop a new Feedback Structure and a Local-Global Spectral Block to alleviate the difficulty in spatial and spectral feature extraction.

Hyperspectral Image Super-Resolution Image Super-Resolution

Remote Sensing Image Change Detection with Transformers

5 code implementations27 Feb 2021 Hao Chen, Zipeng Qi, Zhenwei Shi

To achieve this, we express the bitemporal image into a few tokens, and use a transformer encoder to model contexts in the compact token-based space-time.

Building change detection for remote sensing images Change Detection

NeuralMagicEye: Learning to See and Understand the Scene Behind an Autostereogram

1 code implementation31 Dec 2020 Zhengxia Zou, Tianyang Shi, Yi Yuan, Zhenwei Shi

This paper studies an interesting question that whether a deep CNN can be trained to recover the depth behind an autostereogram and understand its content.

Stylized Neural Painting

4 code implementations CVPR 2021 Zhengxia Zou, Tianyang Shi, Shuang Qiu, Yi Yuan, Zhenwei Shi

Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering.

Disentanglement Image-to-Image Translation +2

Face-to-Parameter Translation for Game Character Auto-Creation

no code implementations ICCV 2019 Tianyang Shi, Yi Yuan, Changjie Fan, Zhengxia Zou, Zhenwei Shi, Yong liu

Character customization system is an important component in Role-Playing Games (RPGs), where players are allowed to edit the facial appearance of their in-game characters with their own preferences rather than using default templates.

Style Transfer Translation

Object Detection in 20 Years: A Survey

1 code implementation13 May 2019 Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, Jieping Ye

Object detection, as of one the most fundamental and challenging problems in computer vision, has received great attention in recent years.

Face Detection Object +4

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