Libao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Libao Zhang has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
Jue Zhang
School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia
10 shared publications- Hanlin Wu
School of Information Science and Technology, Beijing Foreign Studies University, Beijing, China
6 shared publications - Jie Ma
School of Information Science and Technology, Beijing Foreign Studies University, Beijing, China
6 shared publications - Ning Ni
School of Artificial Intelligence, Beijing Normal University, Beijing, China
6 shared publications Bingchang Qiu
College of Information Science and Technology, Beijing Normal University, Beijing, China
4 shared publicationsRuohui Zheng
Beijing Normal University
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2139-2148
AIR-Det: Asymmetric Multimodal Object Detection via Main-Conditioned Residual Learning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2139-2148
Open AccessAIR-Det: Asymmetric Multimodal Object Detection via Main-Conditioned Residual Learning
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16980-16987
Towards a New Paradigm of Remote Sensing Dehazing: A Diagnostic Benchmark
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 16980-16987
Open AccessTowards a New Paradigm of Remote Sensing Dehazing: A Diagnostic Benchmark
- 4 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-16
Building Segmentation of Hazy Aerial Images via Collaborative Decoupling Knowledge Learning
Building segmentation from aerial images is critical for applications such as urban planning and disaster management. However, haze severely degrades image quality, leading to radiance distortion, reduced contrast, and inaccurate segmentation. These degradations introduce two major challenges: 1) conventional methods typically treat dehazing and segmentation as separate tasks, which causes error accumulation and limits performance in haze-laden scenarios; and 2) the diverse scales of buildings and haze-induced domain shifts hinder robust feature representation and accurate boundary delineation. To address these issues, we propose a collaborative decoupling knowledge learning (CDKL) framework that jointly performs dehazing and segmentation within a unified model. Specifically, a dual-branch decoupled network (D-Net) separates image restoration and segmentation, while a bidirectional feature co-interaction module (BFCIM) enables cross-task guidance: segmentation features refine dehazing for clearer structural details, and dehazing features enhance segmentation to resolve haze-induced ambiguities. Furthermore, a teacher network (T-Net) pretrained on clear aerial images guides D-Net through a collaborative knowledge transfer (CKT) system, which aligns features across domains using multilevel strategies, thereby mitigating distribution shifts and improving robustness. Extensive experiments on synthetic and real hazy aerial datasets demonstrate that CDKL achieves state-of-the-art performance, delivering significant gains in segmentation accuracy and robustness across diverse haze conditions. The source code is available at https://github.com/Shan-rs/CDKL.git
- 4 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-16
Building Segmentation of Hazy Aerial Images via Collaborative Decoupling Knowledge Learning
Building segmentation from aerial images is critical for applications such as urban planning and disaster management. However, haze severely degrades image quality, leading to radiance distortion, reduced contrast, and inaccurate segmentation. These degradations introduce two major challenges: 1) conventional methods typically treat dehazing and segmentation as separate tasks, which causes error accumulation and limits performance in haze-laden scenarios; and 2) the diverse scales of buildings and haze-induced domain shifts hinder robust feature representation and accurate boundary delineation. To address these issues, we propose a collaborative decoupling knowledge learning (CDKL) framework that jointly performs dehazing and segmentation within a unified model. Specifically, a dual-branch decoupled network (D-Net) separates image restoration and segmentation, while a bidirectional feature co-interaction module (BFCIM) enables cross-task guidance: segmentation features refine dehazing for clearer structural details, and dehazing features enhance segmentation to resolve haze-induced ambiguities. Furthermore, a teacher network (T-Net) pretrained on clear aerial images guides D-Net through a collaborative knowledge transfer (CKT) system, which aligns features across domains using multilevel strategies, thereby mitigating distribution shifts and improving robustness. Extensive experiments on synthetic and real hazy aerial datasets demonstrate that CDKL achieves state-of-the-art performance, delivering significant gains in segmentation accuracy and robustness across diverse haze conditions. The source code is available at https://github.com/Shan-rs/CDKL.git
- 19 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-17
Satellite Video Continuous Space–Time Super-Resolution via Mask-Based Temporal-Aware Warping and Cross-Level Frequency Integration
The rapid advancement of remote sensing technology has driven a growing demand for high-quality satellite video. However, constrained by transmission bandwidth and storage costs, satellite videos are typically stored and transmitted at low spatial resolutions and frame rates. As a key solution, space-time super-resolution (STSR) aims to enhance video quality. Unfortunately, existing satellite video STSR methods fail to effectively model inter-frame continuity and, consequently, only support a fixed upsampling scale, which restricts their flexibility and practical applicability. To address this challenge, we propose a novel continuous STSR (CSTSR) framework for satellite videos, termed SV-CSTSR. Specifically, first, we develop a spatial-frequency joint modulation block (SFJMB), which aims to jointly mine the fine-grained features of satellite videos in the spatial and frequency domains by using a dual-branch structure. Second, we propose a mask-based temporal-aware warping module (MTWM) to model continuous feature representations in the temporal dimension by modulating feature warping with a time factor, enabling frame interpolation at arbitrary times. Third, we design an inter-frame deformable attention module (IDAM), which can explore inter-frame dependencies to achieve effective information fusion by adaptively selecting the positions of key and value pairs in a data-dependent manner. Finally, we propose a cross-level frequency integration module (CFIM) for continuous-scale upsampling. CFIM aims to activate channel responses through frequency selection, thereby achieving adaptive integration of cross-level frequency latent codes to learn feature representations of satellite videos at arbitrary resolution. Extensive experiments demonstrate that the proposed SV-CSTSR surpasses state-of-the-art methods, achieving superior quantitative accuracy and perceptual fidelity.
- 19 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 64  (01962892) , 1-17
Satellite Video Continuous Space–Time Super-Resolution via Mask-Based Temporal-Aware Warping and Cross-Level Frequency Integration
The rapid advancement of remote sensing technology has driven a growing demand for high-quality satellite video. However, constrained by transmission bandwidth and storage costs, satellite videos are typically stored and transmitted at low spatial resolutions and frame rates. As a key solution, space-time super-resolution (STSR) aims to enhance video quality. Unfortunately, existing satellite video STSR methods fail to effectively model inter-frame continuity and, consequently, only support a fixed upsampling scale, which restricts their flexibility and practical applicability. To address this challenge, we propose a novel continuous STSR (CSTSR) framework for satellite videos, termed SV-CSTSR. Specifically, first, we develop a spatial-frequency joint modulation block (SFJMB), which aims to jointly mine the fine-grained features of satellite videos in the spatial and frequency domains by using a dual-branch structure. Second, we propose a mask-based temporal-aware warping module (MTWM) to model continuous feature representations in the temporal dimension by modulating feature warping with a time factor, enabling frame interpolation at arbitrary times. Third, we design an inter-frame deformable attention module (IDAM), which can explore inter-frame dependencies to achieve effective information fusion by adaptively selecting the positions of key and value pairs in a data-dependent manner. Finally, we propose a cross-level frequency integration module (CFIM) for continuous-scale upsampling. CFIM aims to activate channel responses through frequency selection, thereby achieving adaptive integration of cross-level frequency latent codes to learn feature representations of satellite videos at arbitrary resolution. Extensive experiments demonstrate that the proposed SV-CSTSR surpasses state-of-the-art methods, achieving superior quantitative accuracy and perceptual fidelity.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8968-8977
CLIP-HNet: Hybrid Network with Cross-Modal Guidance for Self-Supervised Remote Sensing Dehazing
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8968-8977
Open AccessCLIP-HNet: Hybrid Network with Cross-Modal Guidance for Self-Supervised Remote Sensing Dehazing
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8596-8605
Saliency-Guided Adaptive Random Diffusion for Remote Sensing Images Restoration with Cloud and Haze
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8596-8605
Open AccessSaliency-Guided Adaptive Random Diffusion for Remote Sensing Images Restoration with Cloud and Haze
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-16
Confidence-Guided Joint Complementary Learning for Weakly Annotated Remote Sensing Object Segmentation
Object segmentation from weakly annotated remote sensing images (RSIs) is an essential task that helps substantially reduce pixelwise labeling costs. Although mainstream multistage methods have achieved great performance, they generally suffer from high implementation complexity, which limits their practical application. On the other hand, for a single-stage scheme that can be trained in one cycle, error accumulation during joint optimization results in performance degradation. To address these issues, we propose a confidence-guided joint complementary learning (CGJCL) framework for remote sensing object segmentation under image-level annotations that can be easily trained in a single stage and achieves satisfactory performance. CGJCL integrates the localization and segmentation network into a unified framework that employs a joint complementary learning strategy, collaboratively enhancing the performance of each subnetwork. First, a confidence-guided pseudolabel refinement (CGPLR) module is developed to fuse the complementary semantic information of the localization clues and the object boundary/structure details learned from each subnetwork to generate high-quality pseudolabels (PLs) and alleviate error accumulation. Second, a dual self-supervised multiscale consistency (DSMC) loss is presented to both explicitly and implicitly utilize consistency regularization, enabling the promotion of model robustness on multiscale objects and preventing overfitting on false-annotated pixels in noisy PLs. Third, a locally enhanced feature aggregation network is proposed to integrate the multilevel semantic features and alleviate low-level noise interference, producing precise segmentation masks. Extensive evaluation on three RSI datasets demonstrates that the proposed method yields superior performance compared with recent single-stage techniques and several multistage methods, thus revealing its effectiveness and superiority.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-16
Confidence-Guided Joint Complementary Learning for Weakly Annotated Remote Sensing Object Segmentation
Object segmentation from weakly annotated remote sensing images (RSIs) is an essential task that helps substantially reduce pixelwise labeling costs. Although mainstream multistage methods have achieved great performance, they generally suffer from high implementation complexity, which limits their practical application. On the other hand, for a single-stage scheme that can be trained in one cycle, error accumulation during joint optimization results in performance degradation. To address these issues, we propose a confidence-guided joint complementary learning (CGJCL) framework for remote sensing object segmentation under image-level annotations that can be easily trained in a single stage and achieves satisfactory performance. CGJCL integrates the localization and segmentation network into a unified framework that employs a joint complementary learning strategy, collaboratively enhancing the performance of each subnetwork. First, a confidence-guided pseudolabel refinement (CGPLR) module is developed to fuse the complementary semantic information of the localization clues and the object boundary/structure details learned from each subnetwork to generate high-quality pseudolabels (PLs) and alleviate error accumulation. Second, a dual self-supervised multiscale consistency (DSMC) loss is presented to both explicitly and implicitly utilize consistency regularization, enabling the promotion of model robustness on multiscale objects and preventing overfitting on false-annotated pixels in noisy PLs. Third, a locally enhanced feature aggregation network is proposed to integrate the multilevel semantic features and alleviate low-level noise interference, producing precise segmentation masks. Extensive evaluation on three RSI datasets demonstrates that the proposed method yields superior performance compared with recent single-stage techniques and several multistage methods, thus revealing its effectiveness and superiority.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-16
Object Segmentation Based on Pseudo Supervision Relearning Under Extremely Weak Annotations for Remote Sensing Images
Weakly annotated object segmentation for remote sensing images (RSIs) has attracted lots of attention due to its low labeling costs. However, annotating a huge amount of multi-class RSIs with image labels is still highly dependent on specific expert knowledge and thus requires considerable labeling costs. In this paper, intending to further alleviate the labor-intensive labeling costs, we introduce a novel extremely weak annotation condition. In this condition, a substantial portion of samples are unlabeled, while merely a small number of samples are labeled with inexact image-level annotations. To achieve object segmentation under extremely weak annotations, we propose Pseudo Supervision Re-Learning (PSRL), a novel three-stage framework with the core insight of effectively harnessing the potentially valuable supervision clues stored in abundant unlabeled data. In the first stage, the extremely weak annotations are switched to fine-grained but noisy pseudo-supervision with the aid of image-level semantic learning and attention-guided data augmentation. Then, a category-aware dataset re-split strategy based on the masking perturbation mechanism is designed, aiming at adaptively selecting high-quality pixel-wise pseudo masks from the artificially generated pseudo supervision and achieving class-balanced reliable-unreliable labels division. Ultimately, we devise a novel dynamic thresholding strategy guided re-learning network, to take full advantage of the valuable semantic information in the re-split dataset. Experimental results on two public RSI datasets show the effectiveness of the proposed framework. Utilizing less supervised information, the proposed method yields competing results compared to weakly supervised learning-based methods with complete image-level annotations.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63  (01962892) , 1-16
Object Segmentation Based on Pseudo Supervision Relearning Under Extremely Weak Annotations for Remote Sensing Images
Weakly annotated object segmentation for remote sensing images (RSIs) has attracted lots of attention due to its low labeling costs. However, annotating a huge amount of multi-class RSIs with image labels is still highly dependent on specific expert knowledge and thus requires considerable labeling costs. In this paper, intending to further alleviate the labor-intensive labeling costs, we introduce a novel extremely weak annotation condition. In this condition, a substantial portion of samples are unlabeled, while merely a small number of samples are labeled with inexact image-level annotations. To achieve object segmentation under extremely weak annotations, we propose Pseudo Supervision Re-Learning (PSRL), a novel three-stage framework with the core insight of effectively harnessing the potentially valuable supervision clues stored in abundant unlabeled data. In the first stage, the extremely weak annotations are switched to fine-grained but noisy pseudo-supervision with the aid of image-level semantic learning and attention-guided data augmentation. Then, a category-aware dataset re-split strategy based on the masking perturbation mechanism is designed, aiming at adaptively selecting high-quality pixel-wise pseudo masks from the artificially generated pseudo supervision and achieving class-balanced reliable-unreliable labels division. Ultimately, we devise a novel dynamic thresholding strategy guided re-learning network, to take full advantage of the valuable semantic information in the re-split dataset. Experimental results on two public RSI datasets show the effectiveness of the proposed framework. Utilizing less supervised information, the proposed method yields competing results compared to weakly supervised learning-based methods with complete image-level annotations.
- 20 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Semantic Segmentation of Weakly Annotated Remote Sensing Images Based on Feature Adversary and Uncertainty Perception
The rich details in remote sensing images require the expertise of domain experts for annotation, making precise labeling across multiple scenarios challenging. Currently, there is an increasing interest in low-precision image-level annotations. However, errors and omissions are difficult to avoid during the labeling process. How to achieve accurate semantic segmentation under noisy annotations has become an urgent problem that requires resolution. In this paper, we consider the rich features of remote sensing targets and design a weakly labeled semantic segmentation model for remote sensing images based on feature adversary and uncertainty perception. Firstly, we introduce a confidence model voting method to handle missing or incorrect image-level labels. Subsequently, we perform multi-level feature fusion to obtain initial pixel-level pseudo-labels. Finally, leveraging the significant differences in image features across different categories, we design a feature adversarial model and introduce an uncertainty analysis method, improving the utilization of remote sensing image features and enhancing the accuracy of semantic segmentation. The effectiveness of this approach is validated through a comprehensive evaluation of four datasets.
- 20 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 21  (1545598X) , 1-5
Semantic Segmentation of Weakly Annotated Remote Sensing Images Based on Feature Adversary and Uncertainty Perception
The rich details in remote sensing images require the expertise of domain experts for annotation, making precise labeling across multiple scenarios challenging. Currently, there is an increasing interest in low-precision image-level annotations. However, errors and omissions are difficult to avoid during the labeling process. How to achieve accurate semantic segmentation under noisy annotations has become an urgent problem that requires resolution. In this paper, we consider the rich features of remote sensing targets and design a weakly labeled semantic segmentation model for remote sensing images based on feature adversary and uncertainty perception. Firstly, we introduce a confidence model voting method to handle missing or incorrect image-level labels. Subsequently, we perform multi-level feature fusion to obtain initial pixel-level pseudo-labels. Finally, leveraging the significant differences in image features across different categories, we design a feature adversarial model and introduce an uncertainty analysis method, improving the utilization of remote sensing image features and enhancing the accuracy of semantic segmentation. The effectiveness of this approach is validated through a comprehensive evaluation of four datasets.