Liang Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Liang Yao has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Fan Liu
Hohai University, Nanjing, China
8 shared publications - Chuanyi Zhang
Hohai University, Nanjing, China
5 shared publications - Jun Zhou
Griffith University
3 shared publications - Ting Wu
College of Computer Science and Software Engineering, Hohai University, Nanjing, China
3 shared publications Chuanyi Zhang
College of Artificial Intelligence and Automation, Hohai University, Changzhou, China
2 shared publications- Jiale Zhu
College of Computer Science and Software Engineering, Hohai University, Nanjing, China
2 shared publications
Latest Publications
- Open Access
- 26 August 2026
- Published by MDPI AG in Preprints.org
From Perception to Reasoning in Remote Sensing: A Survey and Outlook
With the rapid growth of remote sensing data and multimodal information, foundation models for Earth observation and vision–language geospatial reasoning models have become key drivers of intelligent remote sensing analysis. However, the specific roles and applications of reasoning models in remote sensing remain insufficiently explored. This survey defines RS-Reasoning operationally as task-dependent, multi-step inference whose conclusions are supported by traceable visual, temporal, spatial, or tool-derived evidence and are evaluated beyond final-answer accuracy. We organize the literature into three non-exclusive paradigms according to the dominant mechanism by which reasoning is acquired and executed: supervised reasoning, reinforcement learning–driven reasoning, and agentic or tool-augmented reasoning. We further distinguish reasoning-specific methods from vision–language models that provide semantic alignment, generation, or grounding foundations but do not themselves demonstrate multi-step inference. Across urban analysis, disaster assessment, environmental monitoring, and spatiotemporal question answering, we identify the conditions under which reasoning may add value while separating benchmark capability from validated operational deployment. Our synthesis exposes four persistent limitations: frequent use of synthetic supervision with unevenly reported provenance, outcome-dominant evaluation, weak verification of cross-modal evidence, and fragile long-horizon tool use. We therefore outline a research agenda centered on geography-aware process supervision, multimodal constraint checking, calibrated uncertainty, expert feedback, and robustness tests across sensors, regions, and time. For convenient reference and further research, we maintain a curated collection of related resources at https://github.com/ML4Sustain/Awesome-RS-Reasoning-Models.
- 26 August 2026
- Published by MDPI AG in Preprints.org
Open AccessFrom Perception to Reasoning in Remote Sensing: A Survey and Outlook
With the rapid growth of remote sensing data and multimodal information, foundation models for Earth observation and vision–language geospatial reasoning models have become key drivers of intelligent remote sensing analysis. However, the specific roles and applications of reasoning models in remote sensing remain insufficiently explored. This survey defines RS-Reasoning operationally as task-dependent, multi-step inference whose conclusions are supported by traceable visual, temporal, spatial, or tool-derived evidence and are evaluated beyond final-answer accuracy. We organize the literature into three non-exclusive paradigms according to the dominant mechanism by which reasoning is acquired and executed: supervised reasoning, reinforcement learning–driven reasoning, and agentic or tool-augmented reasoning. We further distinguish reasoning-specific methods from vision–language models that provide semantic alignment, generation, or grounding foundations but do not themselves demonstrate multi-step inference. Across urban analysis, disaster assessment, environmental monitoring, and spatiotemporal question answering, we identify the conditions under which reasoning may add value while separating benchmark capability from validated operational deployment. Our synthesis exposes four persistent limitations: frequent use of synthetic supervision with unevenly reported provenance, outcome-dominant evaluation, weak verification of cross-modal evidence, and fragile long-horizon tool use. We therefore outline a research agenda centered on geography-aware process supervision, multimodal constraint checking, calibrated uncertainty, expert feedback, and robustness tests across sensors, regions, and time. For convenient reference and further research, we maintain a curated collection of related resources at https://github.com/ML4Sustain/Awesome-RS-Reasoning-Models.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Learning Where to Look: VLM-Assisted Efficient Inference for Sparse Aerial Objects Segmentation
Existing high-performance semantic segmentation methods for remote sensing often struggle with the tradeoff between inference efficiency and high-resolution processing, especially in scenarios characterized by sparse object distributions. In this letter, we present a vision-language model (VLM)-empowered framework tailored for efficient semantic segmentation in remote sensing. Technically, we introduce a global object screening (GOS) mechanism designed to prune redundant computations. By leveraging the image–text alignment capabilities of VLMs, this module adaptively filters out background-dominated patches via a confidence-based greedy search strategy. Furthermore, to enhance local discriminability, we propose an efficient semantic feature alignment method, utilizing contrastive learning on a constructed multiscale image–text dataset to bolster fine-grained feature representation. In this manner, the semantic segmentation models can strike a good balance between identification accuracy and inference efficiency. Comprehensive evaluations on three standard benchmarks (iSAID, LoveDA, and Potsdam) reveal that our method delivers a dramatic increase in inference speed [up to $4.39 \times $ frames per second (FPS)] while still maintaining comparable segmentation accuracy. Our code and datasets are available at https://github.com/Ccwuting/VLM-Seg-Acceleration
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 23 (1545598X) , 1-5
Learning Where to Look: VLM-Assisted Efficient Inference for Sparse Aerial Objects Segmentation
Existing high-performance semantic segmentation methods for remote sensing often struggle with the tradeoff between inference efficiency and high-resolution processing, especially in scenarios characterized by sparse object distributions. In this letter, we present a vision-language model (VLM)-empowered framework tailored for efficient semantic segmentation in remote sensing. Technically, we introduce a global object screening (GOS) mechanism designed to prune redundant computations. By leveraging the image–text alignment capabilities of VLMs, this module adaptively filters out background-dominated patches via a confidence-based greedy search strategy. Furthermore, to enhance local discriminability, we propose an efficient semantic feature alignment method, utilizing contrastive learning on a constructed multiscale image–text dataset to bolster fine-grained feature representation. In this manner, the semantic segmentation models can strike a good balance between identification accuracy and inference efficiency. Comprehensive evaluations on three standard benchmarks (iSAID, LoveDA, and Potsdam) reveal that our method delivers a dramatic increase in inference speed [up to $4.39 \times $ frames per second (FPS)] while still maintaining comparable segmentation accuracy. Our code and datasets are available at https://github.com/Ccwuting/VLM-Seg-Acceleration
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12792-12798
UEMM-Air: Enable UAVs to Undertake More Multi-modal Tasks
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 12792-12798
Open AccessUEMM-Air: Enable UAVs to Undertake More Multi-modal Tasks
- Top Cited PapersOpen Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3027-3036
RemoteSAM: Towards Segment Anything for Earth Observation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 3027-3036
Top Cited PapersOpen AccessRemoteSAM: Towards Segment Anything for Earth Observation
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Boost UAV-Based Object Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning
Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three lightweight detection frameworks on two benchmark datasets. Extensive experiments demonstrate that our approach can effectively improve model accuracy and achieve state-of-the-art (SoTA) performance on three datasets. Our code and dataset are publicly available at https://github.com/1e12Leon/SIFDAL.
- 25 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-13
Boost UAV-Based Object Detection via Scale-Invariant Feature Disentanglement and Adversarial Learning
Detecting objects from Unmanned Aerial Vehicles (UAV) is often hindered by a large number of small objects, resulting in low detection accuracy. To address this issue, mainstream approaches typically utilize multi-stage inferences. Despite their remarkable detecting accuracies, real-time efficiency is sacrificed, making them less practical to handle real applications. To this end, we propose to improve the single-stage inference accuracy through learning scale-invariant features. Specifically, a Scale-Invariant Feature Disentangling module is designed to disentangle scale-related and scale-invariant features. Then an Adversarial Feature Learning scheme is employed to enhance disentanglement. Finally, scale-invariant features are leveraged for robust UAV-based object detection. Furthermore, we construct a multi-modal UAV object detection dataset, State-Air, which incorporates annotated UAV state parameters. We apply our approach to three lightweight detection frameworks on two benchmark datasets. Extensive experiments demonstrate that our approach can effectively improve model accuracy and achieve state-of-the-art (SoTA) performance on three datasets. Our code and dataset are publicly available at https://github.com/1e12Leon/SIFDAL.
- Open Access
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
A Encoder-Decoder Framework for Foundation Model-based Remote Sensing Semantic Segmentation
- 3 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessA Encoder-Decoder Framework for Foundation Model-based Remote Sensing Semantic Segmentation
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Domain-Invariant Progressive Knowledge Distillation for UAV-Based Object Detection
Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, unmanned aerial vehicle-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors. Existing methods often overlook the significant differences in feature space caused by the large gap in scale between the teacher and student models. This limitation hampers the efficiency of knowledge transfer during the distillation process. Furthermore, the complex backgrounds in aerial images make it challenging for the student model to efficiently learn the object features. In this letter, we propose a novel KD framework for UAV-OD. Specifically, a progressive distillation approach is designed to alleviate the feature gap between teacher and student models. Then, a new feature alignment method is provided to extract object-related features for enhancing the student model’s knowledge reception efficiency. Finally, extensive experiments are conducted to validate the effectiveness of our proposed approach. The results demonstrate that our proposed method achieves state-of-the-art performance on two datasets.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Domain-Invariant Progressive Knowledge Distillation for UAV-Based Object Detection
Knowledge distillation (KD) is an effective method for compressing models in object detection tasks. Due to limited computational capability, unmanned aerial vehicle-based object detection (UAV-OD) widely adopt the KD technique to obtain lightweight detectors. Existing methods often overlook the significant differences in feature space caused by the large gap in scale between the teacher and student models. This limitation hampers the efficiency of knowledge transfer during the distillation process. Furthermore, the complex backgrounds in aerial images make it challenging for the student model to efficiently learn the object features. In this letter, we propose a novel KD framework for UAV-OD. Specifically, a progressive distillation approach is designed to alleviate the feature gap between teacher and student models. Then, a new feature alignment method is provided to extract object-related features for enhancing the student model’s knowledge reception efficiency. Finally, extensive experiments are conducted to validate the effectiveness of our proposed approach. The results demonstrate that our proposed method achieves state-of-the-art performance on two datasets.