Posts by Collection

publications

Make Baseline Model Stronger: Embedded Knowledge Distillation in Weight-Sharing Based Ensemble Network

Published in BMVC, 2021

Recommended citation: S. Lyu, Q. Zhao, Y. Ma, L. Chen. Make Baseline Model Stronger: Embedded Knowledge Distillation in Weight-Sharing Based Ensemble Network. In BMVC, 2021.
Download Paper

Unsupervised Domain Adaptation for VHR Urban Scene Segmentation via Prompted Foundation Model-based Hybrid Training Joint-Optimized Network

Published in TGRS, 2025

Recommended citation: S. Lyu, Q. Zhao, Y. Sun, G. Cheng, Y. He, G. Wang, J. Ren, and Z. Shi, "Unsupervised Domain Adaptation for VHR Urban Scene Segmentation via Prompted Foundation Model-Based Hybrid Training Joint-Optimized Network," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-17, 2025, Art no. 4409117, doi: 10.1109/TGRS.2025.3564216.
Download Paper

Online Self-Training Driven Attention-Guided Self-Mimicking Network for Semantic Segmentation

Published in TNNLS, 2025

Recommended citation: S. Lyu, Q. Zhao, H. Zhang, G. Cheng and C. Yang, "Online Self-Training Driven Attention-Guided Self-Mimicking Network for Semantic Segmentation," in IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 10, pp. 19437-19451, Oct. 2025, doi: 10.1109/TNNLS.2025.3577327.
Download Paper

Enhancing Drone-based Fire Detection with Flame-Specific Attention and Optimized Feature Fusion

Published in JAG, 2025

Recommended citation: Q. Wang, S. Guan, S. Lyu*, G. Cheng, Enhancing drone-based fire detection with flame-specific attention and optimized feature fusion, International Journal of Applied Earth Observation and Geoinformation, Volume 142, 2025, 104655.
Download Paper

Unsupervised Cross-Domain Semantic Segmentation on Multi-Modality Ovarian Tumor Ultrasound Data

Published in PR, 2025

Recommended citation: S. Lyu, Q. Zhao, W. Bai, L. Cai, G. Cheng, G. Cui, M. Yang, L. Chen, H. Zhou, Unsupervised cross-domain semantic segmentation on multi-modality ovarian tumor ultrasound data, Pattern Recognition, Volume 171, Part B, 2026, 112311.
Download Paper

TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios

Published in ICCV Workshop, 2025

Recommended citation: X. Zhu*, S. Lyu*, X. Wang, and Q. Zhao. TPH-YOLOv5: Improved YOLOv5 based on Transformer Prediction Head for Object Detection on Drone-Captured Scenarios. In ICCVW, 2021: 2778-2788.
Download Paper

ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck

Published in ICML, 2025

Recommended citation: Z. Zhou, W. Feng, Q. Zhang, S. Lyu*, Q. Zhao, and G. Cheng. ROME is Forged in Adversity: Robust Distilled Datasets via Information Bottleneck. In ICML, 2025.
Download Paper

Vital: A Multimodality Dataset and Benchmark for Multi-pathological Ovarian Tumor Recognition

Published in ESWA, 2025

Recommended citation: Y. Zhou, L. Chen, G. Cui, W. Bai, Y. Guo, S. Lyu*, G. Cheng, and Q. Zhao, ViTaL: A multimodality dataset and benchmark for multi-pathological ovarian tumor recognition, Expert Systems with Applications, Volume 303,2026, 130650.
Download Paper

Learn From Past to Future: Exploiting Self-Training and Curriculum Learning in Remote Sensing Class-Incremental Semantic Segmentation

Published in TGRS, 2025

Recommended citation: R. Ren, H. Zhao, Y. Wang, S. Lyu*, G. Wang, G. Cheng, Q. Zhao, and J. Ren, "Learn From Past to Future: Exploiting Self-Training and Curriculum Learning in Remote Sensing Class-Incremental Semantic Segmentation," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-15, 2025, Art no. 5657215, doi: 10.1109/TGRS.2025.3643913.
Download Paper

The Teacher-Student Interactive Cycle: Joint Optimization with Inner-Loop Self-Distillation in Prompted Foundation Models for Efficient Semantic Segmentation

Published in TCSVT, 2026

Recommended citation: M. Li, Q. Zhao, S. Lyu*, J. Jiang, L. Zou, D. Yao, G. Cheng, and C. Yang, "The Teacher–Student Interactive Cycle: Joint Optimization With Inner-Loop Self-Distillation in Prompted Foundation Models for Efficient Semantic Segmentation," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 36, no. 7, pp. 10763-10779, July 2026, doi: 10.1109/TCSVT.2026.3665905.
Download Paper