Zhuo Zheng

All Publications

• Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE Zheng, Z., Ermon, S., Kim, D., Zhang, L., Zhong, Y. 2025; 47 (2): 725-741

  Abstract

  Our understanding of the temporal dynamics of the Earth's surface has been significantly advanced by deep vision models, which often require a massive amount of labeled multi-temporal images for training. However, collecting, preprocessing, and annotating multi-temporal remote sensing images at scale is non-trivial since it is expensive and knowledge-intensive. In this paper, we present scalable multi-temporal change data generators based on generative models, which are cheap and automatic, alleviating these data problems. Our main idea is to simulate a stochastic change process over time. We describe the stochastic change process as a probabilistic graphical model, namely the generative probabilistic change model (GPCM), which factorizes the complex simulation problem into two more tractable sub-problems, i.e., condition-level change event simulation and image-level semantic change synthesis. To solve these two problems, we present Changen2, a GPCM implemented with a resolution-scalable diffusion transformer which can generate time series of remote sensing images and corresponding semantic and change labels from labeled and even unlabeled single-temporal images. Changen2 is a "generative change foundation model" that can be trained at scale via self-supervision, and is capable of producing change supervisory signals from unlabeled single-temporal images. Unlike existing "foundation models", our generative change foundation model synthesizes change data to train task-specific foundation models for change detection. The resulting model possesses inherent zero-shot change detection capabilities and excellent transferability. Comprehensive experiments suggest Changen2 has superior spatiotemporal scalability in data generation, e.g., Changen2 model trained on 256 2 pixel single-temporal images can yield time series of any length and resolutions of 1,024 2 pixels. Changen2 pre-trained models exhibit superior zero-shot performance (narrowing the performance gap to 3% on LEVIR-CD and approximately 10% on both S2Looking and SECOND, compared to fully supervised counterpart) and transferability across multiple types of change tasks, including ordinary and off-nadir building change, land-use/land-cover change, and disaster assessment. The model and datasets are available at https://github.com/Z-Zheng/pytorch-change-models.

  View details for DOI 10.1109/TPAMI.2024.3475824

  View details for Web of Science ID 001395340500042

  View details for PubMedID 39388323

• Single-Temporal Supervised Learning for Universal Remote Sensing Change Detection INTERNATIONAL JOURNAL OF COMPUTER VISION Zheng, Z., Zhong, Y., Ma, A., Zhang, L. 2024

  View details for DOI 10.1007/s11263-024-02141-4

  View details for Web of Science ID 001250359600001

• FarSeg++: Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery. IEEE transactions on pattern analysis and machine intelligence Zheng, Z., Zhong, Y., Wang, J., Ma, A., Zhang, L. 2023; PP

  Abstract

  Geospatial object segmentation, a fundamental Earth vision task, always suffers from scale variation, the larger intra-class variance of background, and foreground-background imbalance in high spatial resolution (HSR) remote sensing imagery. Generic semantic segmentation methods mainly focus on the scale variation in natural scenarios. However, the other two problems are insufficiently considered in large area Earth observation scenarios. In this paper, we propose a foreground-aware relation network (FarSeg++) from the perspectives of relation-based, optimization-based, and objectness-based foreground modeling, alleviating the above two problems. From the perspective of the relations, the foreground-scene relation module improves the discrimination of the foreground features via the foreground-correlated contexts associated with the object-scene relation. From the perspective of optimization, foreground-aware optimization is proposed to focus on foreground examples and hard examples of the background during training to achieve a balanced optimization. Besides, from the perspective of objectness, a foreground-aware decoder is proposed to improve the objectness representation, alleviating the objectness prediction problem that is the main bottleneck revealed by an empirical upper bound analysis. We also introduce a new large-scale high-resolution urban vehicle segmentation dataset to verify the effectiveness of the proposed method and push the development of objectness prediction further forward. The experimental results suggest that FarSeg++ is superior to the state-of-the-art generic semantic segmentation methods and can achieve a better trade-off between speed and accuracy. The code and model are available at: https://github.com/Z-Zheng/FarSeg.

  View details for DOI 10.1109/TPAMI.2023.3296757

  View details for PubMedID 37467086

• Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process Zheng, Z., Tian, S., Ma, A., Zhang, L., Zhong, Y., IEEE IEEE COMPUTER SOC. 2023: 21761-21770

  View details for DOI 10.1109/ICCV51070.2023.01994

  View details for Web of Science ID 001169500506036

• ChangeMask: Deep multi-task encoder-transformer-decoder architecture for semantic change detection ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Zheng, Z., Zhong, Y., Tian, S., Ma, A., Zhang, L. 2022; 183: 228-239

  View details for DOI 10.1016/j.isprsjprs.2021.10.015

  View details for Web of Science ID 000782582900002

• Building damage assessment for rapid disaster response with a deep object-based semantic change detection framework: From natural disasters to man-made disasters REMOTE SENSING OF ENVIRONMENT Zheng, Z., Zhong, Y., Wang, J., Ma, A., Zhang, L. 2021; 265

  View details for DOI 10.1016/j.rse.2021.112636

  View details for Web of Science ID 000697024400003

• Deep multisensor learning for missing-modality all-weather mapping ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Zheng, Z., Ma, A., Zhang, L., Zhong, Y. 2021; 174: 254-264

  View details for DOI 10.1016/j.isprsjprs.2020.12.009

  View details for Web of Science ID 000640987800017

• Change is Everywhere: Single-Temporal Supervised Object Change Detection in Remote Sensing Imagery Zheng, Z., Ma, A., Zhang, L., Zhong, Y., IEEE IEEE. 2021: 15173-15182

  View details for DOI 10.1109/ICCV48922.2021.01491

  View details for Web of Science ID 000798743205035

• FPGA: Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Zheng, Z., Zhong, Y., Ma, A., Zhang, L. 2020; 58 (8): 5612-5626

  View details for DOI 10.1109/TGRS.2020.2967821

  View details for Web of Science ID 000552371900031

• HyNet: Hyper-scale object detection network framework for multiple spatial resolution remote sensing imagery ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Zheng, Z., Zhong, Y., Ma, A., Han, X., Zhao, J., Liu, Y., Zhang, L. 2020; 166: 1-14

  View details for DOI 10.1016/j.isprsjprs.2020.04.019

  View details for Web of Science ID 000551268300001

• Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery Zheng, Z., Zhong, Y., Wang, J., Ma, A., IEEE IEEE. 2020: 4095-4104

  View details for DOI 10.1109/CVPR42600.2020.00415

  View details for Web of Science ID 000620679504037

• Visual state space models with spiral selective scan for referring remote-sensing image segmentation GEO-SPATIAL INFORMATION SCIENCE Shen, W., Ma, A., Zheng, Z., Wang, J., Zhong, Y. 2026

  View details for DOI 10.1080/10095020.2026.2642509

  View details for Web of Science ID 001717360100001

• Spatial-X fusion for multi-source satellite imageries REMOTE SENSING OF ENVIRONMENT He, J., Lin, L., Zheng, Z., Yuan, Q., Li, J., Zhang, L., Zhu, X. 2026; 334

  View details for DOI 10.1016/j.rse.2025.115214

  View details for Web of Science ID 001674210100001

• Artificial Intelligence for Earthquake Response: Outcomes and insights from a global spaceborne rapid mapping challenge IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE Ebel, P., El Baz, M., Wang, J., Xuan, W., Qi, H., Zheng, Z., Yokoya, N., Park, J., Park, J., Elskens, A., Charles, E., Modica, I., Foltz, Z., Bally, P., Bossung, C., Chini, M., Longepe, N., Meoni, G. 2026

  View details for DOI 10.1109/MGRS.2026.3653995

  View details for Web of Science ID 001691145200001

• DreamCD: A change-label-free framework for change detection via a weakly conditional semantic diffusion model in optical VHR imagery INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION Tang, K., Zheng, Z., Chen, H., Chen, X., Chen, J. 2026; 146

  View details for DOI 10.1016/j.jag.2026.105125

  View details for Web of Science ID 001680226300001

• Dynamic, high-resolution poverty measurement in data-scarce environments JOURNAL OF DEVELOPMENT ECONOMICS Zheng, Z., Wu, T., Lee, R., Newhouse, D., Kilic, T., Burke, M., Ermon, S., Lobell, D. B. 2026; 179

  View details for DOI 10.1016/j.jdeveco.2025.103691

  View details for Web of Science ID 001631184900002

• Remote Sensing-Oriented Small-Object Detection Based on Rotation-Normalized Prompting Segment Anything Model IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Chai, B., Wang, J., Zheng, Z., Chen, L., Gong, X., Liu, W. 2026; 64

  View details for DOI 10.1109/TGRS.2026.3684509

  View details for Web of Science ID 001748492100014

• UPchange: Unpaired Supervised Semantic Change Detection for High-Resolution Remote Sensing Imagery IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Yang, J., Ma, A., Tian, S., Zheng, Z., Wu, W., Zhong, Y. 2026; 64

  View details for DOI 10.1109/TGRS.2026.3704148

  View details for Web of Science ID 001807852600024

• Knowledge-Guided Vision-Language Models Prompt Learning for Open-Vocabulary Remote Sensing Image Scene Classification IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Ma, A., Shen, W., Yang, R., Zheng, Z., Wang, J., Zhong, Y. 2026; 64

  View details for DOI 10.1109/TGRS.2026.3715502

  View details for Web of Science ID 001841764500016

• Neural disaster simulation for transferable building damage assessment REMOTE SENSING OF ENVIRONMENT Zheng, Z., Zhong, Y., Wan, Z., Zhang, L., Ermon, S. 2025; 331

  View details for DOI 10.1016/j.rse.2025.114979

  View details for Web of Science ID 001574541100001

• CityVLM: Towards sustainable urban development via multi-view coordinated vision-language model ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Wang, J., Xuan, W., Qi, H., Chen, Z., Chen, H., Zheng, Z., Xia, J., Zhong, Y., Yokoya, N. 2026; 232: 62-74

  View details for DOI 10.1016/j.isprsjprs.2025.11.030

  View details for Web of Science ID 001635194400001

• Remote sensing intelligent interpretation brain: Real-time intelligent understanding of the Earth. PNAS nexus Wan, Y., Zhang, C., Ma, A., Chen, Z., Sun, C., Wang, J., Zheng, Z., Bao, F., Zhang, L., Zhong, Y. 2025; 4 (6): pgaf182

  Abstract

  The large-scale understanding of nature and human activities in real time cannot be separated from Earth observation. Existing monitoring techniques, however, rely primarily on offline processing, with a separation between software and hardware in collection, processing and transmission processes. This limits the ability and timeliness in response to emergency tasks such as disaster relief and nighttime rescue. Our brain can process real-time information across different scales and modalities through perception, cognition, transmission, and decision-making, to take informed actions rapidly. Such an intelligent ability inspires us to establish a novel remote sensing intelligent interpretation brain (RSI2_Brain), by combining multimodal data processing, network transmission and communication on-the-fly, to demonstrate new understanding of the Earth. The RSI2_Brain can operate as online acquisition, real-time processing and transmission with low computational power and communication blocking constraints. It, therefore, has practical utility and wide applicability in extremely harsh conditions, providing all-day and online response automatically.

  View details for DOI 10.1093/pnasnexus/pgaf182

  View details for PubMedID 40501452

  View details for PubMedCentralID PMC12152476

• Learning Temporal Consistency for High Spatial Resolution Remote Sensing Imagery Semantic Change Detection IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Tian, S., Ma, A., Zheng, Z., Tan, X., Zhong, Y. 2025; 63

  View details for DOI 10.1109/TGRS.2025.3561021

  View details for Web of Science ID 001488488600002

• Advancing Weakly-Supervised Change Detection in Satellite Images via Adversarial Class Prompting IEEE TRANSACTIONS ON IMAGE PROCESSING Zhao, Z., Wu, C., Wang, D., Chen, H., Chen, C., Zheng, Z., Du, B., Zhang, L. 2025; 34: 7065-7078

  Abstract

  Weakly-Supervised Change Detection (WSCD) aims to distinguish specific object changes (e.g., objects appearing or disappearing) from background variations (e.g., environmental changes due to light, weather, or seasonal shifts) in paired satellite images, relying only on paired image (i.e., image-level) classification labels. This technique significantly reduces the need for dense annotations required in fully-supervised change detection. However, as image-level supervision only indicates whether objects have changed in a scene, WSCD methods often misclassify background variations as object changes, especially in complex remote-sensing scenarios. In this work, we propose an Adversarial Class Prompting (AdvCP) method to address this co-occurring noise problem, including two phases: a) Adversarial Prompt Mining: After each training iteration, we introduce adversarial prompting perturbations, using incorrect one-hot image-level labels to activate erroneous feature mappings. This process reveals co-occurring adversarial samples under weak supervision, namely background variation features that are likely to be misclassified as object changes. b) Adversarial Sample Rectification: We integrate these adversarially prompt-activated pixel samples into training by constructing an online global prototype. This prototype is built from an exponentially weighted moving average of the current batch and all historical training data. Serving as an unbiased anchor, the global prototype guides the rectification of adversarial pixel samples. Our AdvCP can be seamlessly integrated into current WSCD methods without adding additional inference cost. Experiments on ConvNet, Transformer, and Segment Anything Model (SAM)-based baselines demonstrate significant performance enhancements, achieving up to 7.37%, 7.46%, and 6.56% IoU improvements on the WHU-CD, LEVIR-CD, and DSIFN-CD datasets. Furthermore, we demonstrate the generalizability of AdvCP to other multi-class weakly-supervised dense prediction scenarios. Code is available at https://github.com/zhenghuizhao/AdvCP.

  View details for DOI 10.1109/TIP.2025.3623260

  View details for Web of Science ID 001611600900001

  View details for PubMedID 41134954

• Open-CD: A Comprehensive Toolbox for Change Detection Li, K., Jiang, J., Han, C., Deng, Y., Chen, K., Zheng, Z., Chen, H., Liu, Z., Gu, Y., Zou, Z., Shi, Z., Fang, S., Meng, D., Wang, Z., Cao, X., ACM ASSOC COMPUTING MACHINERY. 2025: 13608-13612

  View details for DOI 10.1145/3746027.3756881

  View details for Web of Science ID 001671135600692

• Towards transferable building damage assessment via unsupervised single-temporal change adaptation REMOTE SENSING OF ENVIRONMENT Zheng, Z., Zhong, Y., Zhang, L., Burke, M., Lobell, D. B., Ermon, S. 2024; 315

  View details for DOI 10.1016/j.rse.2024.114416

  View details for Web of Science ID 001329591400001

• Unifying remote sensing change detection via deep probabilistic change models: From principles, models to applications ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Zheng, Z., Zhong, Y., Zhao, J., Ma, A., Zhang, L. 2024; 215: 239-255

  View details for DOI 10.1016/j.isprsjprs.2024.07.001

  View details for Web of Science ID 001273221200001

• Global road extraction using a pseudo-label guided framework: from benchmark dataset to cross-region semi-supervised learning GEO-SPATIAL INFORMATION SCIENCE Lu, X., Zhong, Y., Zheng, Z., Wang, J., Chen, D., Su, Y. 2024

  View details for DOI 10.1080/10095020.2024.2362760

  View details for Web of Science ID 001251618600001

• EarthVQANet: Multi-task visual question answering for remote sensing image understanding ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Wang, J., Ma, A., Chen, Z., Zheng, Z., Wan, Y., Zhang, L., Zhong, Y. 2024; 212: 422-439

  View details for DOI 10.1016/j.isprsjprs.2024.05.001

  View details for Web of Science ID 001243433300001

• LoveNAS: Towards multi-scene land-cover mapping via hierarchical searching adaptive network ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Wang, J., Zhong, Y., Ma, A., Zheng, Z., Wan, Y., Zhang, L. 2024; 209: 265-278

  View details for DOI 10.1016/j.isprsjprs.2024.01.011

  View details for Web of Science ID 001200052300001

• Adaptive Self-Supporting Prototype Learning for Remote Sensing Few-Shot Semantic Segmentation IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Shen, W., Ma, A., Wang, J., Zheng, Z., Zhong, Y. 2024; 62

  View details for DOI 10.1109/TGRS.2024.3435086

  View details for Web of Science ID 001289662900034

• Segment Any Change Zheng, Z., Zhong, Y., Zhang, L., Ermon, S. edited by Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., Zhang, C. NEURAL INFORMATION PROCESSING SYSTEMS (NIPS). 2024

  View details for Web of Science ID 001633239900181

• MAPCHANGE: ENHANCING SEMANTIC CHANGE DETECTION WITH TEMPORALINVARIANT HISTORICAL MAPS BASED ON DEEP TRIPLET NETWORK Liu, Y., Shi, S., Zheng, Z., Wang, J., Tian, S., Zhong, Y., IEEE IEEE. 2024: 7653-7656

  View details for DOI 10.1109/IGARSS53475.2024.10640532

  View details for Web of Science ID 001415226902111

• LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images Zhang, J., Fang, I., Wu, H., Kaushik, A., Rodriguez, A., Zhao, H., Zhang, J., Zheng, Z., Iovita, R., Feng, C., IEEE IEEE COMPUTER SOC. 2024: 22563-22573

  View details for DOI 10.1109/CVPR52733.2024.02129

  View details for Web of Science ID 001342515505086

• EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering Wang, J., Zheng, Z., Chen, Z., Ma, A., Zhong, Y. edited by Dy, J., Natarajan, S., Wooldridge, M. ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2024: 5481-5489

  View details for Web of Science ID 001239936300043

• Temporal-agnostic change region proposal for semantic change detection ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Tian, S., Tan, X., Ma, A., Zheng, Z., Zhang, L., Zhong, Y. 2023; 204: 306-320

  View details for DOI 10.1016/j.isprsjprs.2023.06.017

  View details for Web of Science ID 001086073500001

• Explicable Fine-Grained Aircraft Recognition Via Deep Part Parsing Prior Framework for High-Resolution Remote Sensing Imagery. IEEE transactions on cybernetics Chen, D., Zhong, Y., Ma, A., Zheng, Z., Zhang, L. 2023; PP

  Abstract

  Aircraft recognition is crucial in both civil and military fields, and high-spatial resolution remote sensing has emerged as a practical approach. However, existing data-driven methods fail to locate discriminative regions for effective feature extraction due to limited training data, leading to poor recognition performance. To address this issue, we propose a knowledge-driven deep learning method called the explicable aircraft recognition framework based on a part parsing prior (APPEAR). APPEAR explicitly models the aircraft's rigid structure as a pixel-level part parsing prior, dividing it into five parts: 1) the nose; 2) left wing; 3) right wing; 4) fuselage; and 5) tail. This fine-grained prior provides reliable part locations to delineate aircraft architecture and imposes spatial constraints among the parts, effectively reducing the search space for model optimization and identifying subtle interclass differences. A knowledge-driven aircraft part attention (KAPA) module uses this prior to achieving a geometric-invariant representation for identifying discriminative features. Part features are generated by part indexing in a specific order and sequentially embedded into a compact space to obtain a fixed-length representation for each part, invariant to aircraft orientation and scale. The part attention module then takes the embedded part features, adaptively reweights their importance to identify discriminative parts, and aggregates them for recognition. The proposed APPEAR framework is evaluated on two aircraft recognition datasets and achieves superior performance. Moreover, experiments with few-shot learning methods demonstrate the robustness of our framework in different tasks. Ablation analysis illustrates that the fuselage and wings of the aircraft are the most effective parts for recognition.

  View details for DOI 10.1109/TCYB.2023.3293033

  View details for PubMedID 37552595

• Large-scale agricultural greenhouse extraction for remote sensing imagery based on layout attention network: A case study of China ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Chen, D., Ma, A., Zheng, Z., Zhong, Y. 2023; 200: 73-88

  View details for DOI 10.1016/j.isprsjprs.2023.04.020

  View details for Web of Science ID 001007013800001

• Large-scale deep learning based binary and semantic change detection in ultra high resolution remote sensing imagery: From benchmark datasets to urban application ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Tian, S., Zhong, Y., Zheng, Z., Ma, A., Tan, X., Zhang, L. 2022; 193: 164-186

  View details for DOI 10.1016/j.isprsjprs.2022.08.012

  View details for Web of Science ID 000876743000004

• Cross-sensor domain adaptation for high spatial resolution urban land-cover mapping: From airborne to spaceborne imagery REMOTE SENSING OF ENVIRONMENT Wang, J., Ma, A., Zhong, Y., Zheng, Z., Zhang, L. 2022; 277

  View details for DOI 10.1016/j.rse.2022.113058

  View details for Web of Science ID 000804945700001

• GRE AND BEYOND: A GLOBAL ROAD EXTRACTION DATASET Lu, X., Zhong, Y., Zheng, Z., Chen, D., IEEE IEEE. 2022: 3035-3038

  View details for DOI 10.1109/IGARSS46834.2022.9883915

  View details for Web of Science ID 000920916603057

• Cascaded Multi-Task Road Extraction Network for Road Surface, Centerline, and Edge Extraction IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Lu, X., Zhong, Y., Zheng, Z., Chen, D., Su, Y., Ma, A., Zhang, L. 2022; 60

  View details for DOI 10.1109/TGRS.2022.3165817

  View details for Web of Science ID 000794217400005

• A Supervised Progressive Growing Generative Adversarial Network for Remote Sensing Image Scene Classification IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Ma, A., Yu, N., Zheng, Z., Zhong, Y., Zhang, L. 2022; 60

  View details for DOI 10.1109/TGRS.2022.3151405

  View details for Web of Science ID 000773300900029

• National-scale greenhouse mapping for high spatial resolution remote sensing imagery using a dense object dual-task deep learning framework: A case study of China ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Ma, A., Chen, D., Zhong, Y., Zheng, Z., Zhang, L. 2021; 181: 279-294

  View details for DOI 10.1016/j.isprsjprs.2021.08.024

  View details for Web of Science ID 000704454800009

• Cross-domain road detection based on global-local adversarial learning framework from very high resolution satellite imagery ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Lu, X., Zhong, Y., Zheng, Z., Wang, J. 2021; 180: 296-312

  View details for DOI 10.1016/j.isprsjprs.2021.08.018

  View details for Web of Science ID 000697167200020

• FactSeg: Foreground Activation-Driven Small Object Semantic Segmentation in Large-Scale Remote Sensing Imagery IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Ma, A., Wang, J., Zhong, Y., Zheng, Z. 2022; 60

  View details for DOI 10.1109/TGRS.2021.3097148

  View details for Web of Science ID 000732756800001

• Urban road mapping based on an end-to-end road vectorization mapping network framework ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Chen, D., Zhong, Y., Zheng, Z., Ma, A., Lu, X. 2021; 178: 345-365

  View details for DOI 10.1016/j.isprsjprs.2021.05.016

  View details for Web of Science ID 000686383900001

• A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification IEEE TRANSACTIONS ON CYBERNETICS Zhu, Q., Deng, W., Zheng, Z., Zhong, Y., Guan, Q., Lin, W., Zhang, L., Li, D. 2022; 52 (11): 11709-11723

  Abstract

  Deep learning techniques have been widely applied to hyperspectral image (HSI) classification and have achieved great success. However, the deep neural network model has a large parameter space and requires a large number of labeled data. Deep learning methods for HSI classification usually follow a patchwise learning framework. Recently, a fast patch-free global learning (FPGA) architecture was proposed for HSI classification according to global spatial context information. However, FPGA has difficulty in extracting the most discriminative features when the sample data are imbalanced. In this article, a spectral-spatial-dependent global learning (SSDGL) framework based on the global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM) is proposed for insufficient and imbalanced HSI classification. In SSDGL, the hierarchically balanced (H-B) sampling strategy and the weighted softmax loss are proposed to address the imbalanced sample problem. To effectively distinguish similar spectral characteristics of land cover types, the GCL module is introduced to extract the long short-term dependency of spectral features. To learn the most discriminative feature representations, the GJAM module is proposed to extract attention areas. The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods.

  View details for DOI 10.1109/TCYB.2021.3070577

  View details for Web of Science ID 000732244900001

  View details for PubMedID 34033562

• GAMSNet: Globally aware road detection network with multi-scale residual learning ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING Lu, X., Zhong, Y., Zheng, Z., Zhang, L. 2021; 175: 340-352

  View details for DOI 10.1016/j.isprsjprs.2021.03.008

  View details for Web of Science ID 000644695700024

• RSNet: The Search for Remote Sensing Deep Neural Networks in Recognition Tasks IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Wang, J., Zhong, Y., Zheng, Z., Ma, A., Zhang, L. 2021; 59 (3): 2520-2534

  View details for DOI 10.1109/TGRS.2020.3001401

  View details for Web of Science ID 000622319000049

• SENSOR-SPECIFIC ADVERSARIAL NETWORK FOR TRANSFERABLE LAND-COVER CLASSIFICATION Wang, J., Zhong, Y., Zheng, Z., Ma, A., IEEE IEEE. 2021: 7943-7946

  View details for DOI 10.1109/IGARSS47720.2021.9553458

  View details for Web of Science ID 001250139807253

• WEAKLY SUPERVISED SEMANTIC CHANGE DETECTION VIA LABEL REFINEMENT FRAMEWORK Zheng, Z., Liu, Y., Tian, S., Wang, J., Ma, A., Zhong, Y., IEEE IEEE. 2021: 2066-2069

  View details for DOI 10.1109/IGARSS47720.2021.9553768

  View details for Web of Science ID 001250139802067

• COLOR: Cycling, Offline Learning, and Online Representation Framework for Airport and Airplane Detection Using GF-2 Satellite Images IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Zhong, Y., Zheng, Z., Ma, A., Lu, X., Zhang, L. 2020; 58 (12): 8438-8449

  View details for DOI 10.1109/TGRS.2020.2987907

  View details for Web of Science ID 000594389800015

• Edge-Reinforced Convolutional Neural Network for Road Detection in Very-High-Resolution Remote Sensing Imagery PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING Lu, X., Zhong, Y., Zheng, Z., Zhao, J., Zhang, L. 2020; 86 (3): 153-160

  View details for DOI 10.14358/PERS.86.3.153

  View details for Web of Science ID 000516713700003

• A NOVEL GLOBAL-AWARE DEEP NETWORK FOR ROAD DETECTION OF VERY HIGH RESOLUTION REMOTE SENSING IMAGERY Lu, X., Zhong, Y., Zheng, Z., IEEE IEEE. 2020: 2579-2582

  View details for DOI 10.1109/IGARSS39084.2020.9323155

  View details for Web of Science ID 000664335302151

• Multi-Scale and Multi-Task Deep Learning Framework for Automatic Road Extraction IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING Lu, X., Zhong, Y., Zheng, Z., Liu, Y., Zhao, J., Ma, A., Yang, J. 2019; 57 (11): 9362-9377

  View details for DOI 10.1109/TGRS.2019.2926397

  View details for Web of Science ID 000496155200076

• S3NET: TOWARDS REAL-TIME HYPERSPECTRAL IMAGERY CLASSIFICATION Zheng, Z., Zhong, Y., IEEE IEEE. 2019: 3293-3296

  View details for Web of Science ID 000519270603077

• POP-NET: ENCODER-DUAL DECODER FOR SEMANTIC SEGMENTATION AND SINGLE-VIEW HEIGHT ESTIMATION Zheng, Z., Zhong, Y., Wang, J., IEEE IEEE. 2019: 4963-4966

  View details for Web of Science ID 000519270604212

• Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery REMOTE SENSING Gong, X., Xie, Z., Liu, Y., Shi, X., Zheng, Z. 2018; 10 (3)

  View details for DOI 10.3390/rs10030410

  View details for Web of Science ID 000428280100056

• COLOR: CYCLING OFFLINE LEARNING AND ONLINE REPRESENTING FOR REMOTE SENSING DATAFLOW Zheng, Z., Zhong, Y., IEEE IEEE. 2018: 4093-4096

  View details for Web of Science ID 000451039804016

• Multi-channel Pose-aware Convolution Neural Networks for Multi-view Facial Expression Recognition Liu, Y., Zeng, J., Shan, S., Zheng, Z., IEEE IEEE. 2018: 458-465

  View details for DOI 10.1109/FG.2018.00074

  View details for Web of Science ID 000454996700064