朱子聪

朱子聪

办公地址：电子信息楼355
联系电话：18912670517
个人邮箱：zczhu2023@suda.edu.cn

Posts by Collection

portfolio

publications

AOPDet: Automatic Organized Points Detector for Precisely Localizing Objects in Aerial Imagery

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022

AOPDet framework This paper proposes AOPDet, with the core contribution of proposing a non sequential corner representation method as a novel rotation target representation, designing an automatic organization mechanism to guide the model to learn target corners, and designing a dedicated detection head structure. Improved 17.0 mAP compared to baseline on the publicly available aerial dataset, reaching SOTA level.

Recommended citation:
Z. Zhu, X. Sun, W. Diao, K. Chen, G. Xu and K. Fu, "AOPDet: Automatic Organized Points Detector for Precisely Localizing Objects in Aerial Imagery," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-16, 2022, Art no. 5606816, doi: 10.1109/TGRS.2021.3093557.
Download Paper

Invariant Structure Representation for Remote Sensing Object Detection Based on Graph Modeling

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022

GFANet framework This paper proposes GFA Net, with the core contribution of systematically studying the invariant structural features of remote sensing targets, proposing an implicit modeling of target structural features based on graph convolution in the graph focusing process, and designing a graph aggregation network to achieve end-to-end efficient training. The effectiveness of the SOTA method has been validated on mainstream open-source datasets.

Recommended citation:
Z. Zhu, X. Sun, W. Diao, K. Chen, G. Xu and K. Fu, "Invariant Structure Representation for Remote Sensing Object Detection Based on Graph Modeling," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-17, 2022, Art no. 5625217, doi: 10.1109/TGRS.2022.3181686.
Download Paper

CODet: Component Object Detector Extracting Structural Features Based on Target Characteristics

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023

CODet framework This paper proposes CODet detection of remote sensing combined targets, with core contributions including: 1) cross level feature fusion module learning component structure and positional relationships; 2) The noise sparse sample allocation strategy alleviates the problems of classification localization misalignment and sample imbalance. Build a large-scale remote sensing image inference framework to accelerate inference by 3-4 times.

Recommended citation:
Z. Zhu, X. Sun, W. Diao, K. Chen, Q. He, G. Xu and K. Fu, "CODet: Component Object Detector Extracting Structural Features Based on Target Characteristics," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-14, 2023, Art no. 5611914, doi: 10.1109/TGRS.2023.3281331.
Download Paper

RingMo: A Remote Sensing Foundation Model With Masked Image Modeling

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023

RingMo framework This paper proposes a pre training framework for RingMo remote sensing basic model: for the first time, a pre training method based on mask image reconstruction adapted to remote sensing scenes is proposed. SOTA was achieved on eight mainstream datasets across four downstream tasks, validating the effectiveness of generative self supervised learning in the field of remote sensing.

Recommended citation:
X. Sun*, P. Wang*, W. Lu*, Z. Zhu* et al., "RingMo: A Remote Sensing Foundation Model With Masked Image Modeling," in IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-22, 2023, Art no. 5612822, doi: 10.1109/TGRS.2022.3194732.
Download Paper | Download Code

SIRS: Multitask Joint Learning for Remote Sensing Foreground-Entity Image–Text Retrieval

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2024

SIRS framework This paper proposes the SIRS cross modal image text retrieval framework, with core contributions including: 1) semantic guided spatial attention, construction of multi task joint learning branches, filtering out noise and refining foreground features; 2) Adaptive multi-scale weighting improves retrieval efficiency. Significant improvement on open-source datasets, with optional output segmentation masks.

Recommended citation:
Z. Zhu, J. Kang, W. Diao, Y. Feng, J. Li and J. Ni, "SIRS: Multitask Joint Learning for Remote Sensing Foreground-Entity Image–Text Retrieval," in IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-15, 2024, Art no. 5625615, doi: 10.1109/TGRS.2024.3402216.
Download Paper | Download Code

DIAMONDNET: SHIP DETECTION IN REMOTE SENSING IMAGES BY EXTRACTING AND CLUSTERING KEYPOINTS IN A DIAMOND

Published in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2024

DiamondNet framework This paper proposes a ship detection framework based on keypoint extraction: the ship is characterized by five keypoints (center, head and tail, left and right midpoints) distributed in a diamond shape, and a clustering algorithm based on geometric features is designed to aggregate the keypoints. Flexible export of horizontal or rotated boxes to achieve SOTA on two datasets.

Recommended citation:
Z. Zhu, W. Diao, K. Chen, L. Zhao, Z. Yan, W. Zhang, G. Xu and X. Sun, "DiamondNet: Ship Detection in Remote Sensing Images by Extracting and Clustering Keypoints in a Diamond," ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. V-2-2020, pp. 625-632, 2020, doi: 10.5194/isprs-annals-V-2-2020-625-2020.
Download Paper

A PARAMETER-EFFICIENT DIFFERENTIABLE ACTIVE CONTOUR NETWORK FOR PRECISELY BUILDING INSTANCE SEGMENTATION

Published in IEEE International Geoscience and Remote Sensing Symposium, 2024

PDAC framework This paper proposes a PDAC network that uses adapter fine-tuning encoders instead of training from scratch, coupling DNN and ACM with a very small number of parameters to achieve end-to-end building segmentation. On two major building datasets, the effectiveness of the parameter efficient fine-tuning method was verified by achieving better performance than the baseline with nearly half of the computing resources.

Recommended citation:
Z. Zhu, B. Dong, Q. Bu and J. Ni, "A Parameter-Efficient Differentiable Active Contour Network for Precisely Building Instance Segmentation," IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, 2024, pp. 8355-8359, doi: 10.1109/IGARSS53475.2024.10642815.
Download Paper

A Scale-Aware and Discriminative Feature Learning Network for Fine-Grained Rigid Object Recognition

Published in IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2024

SDNet framework This paper proposes the SD Net training framework: based on probability distribution functions, scale soft labels are constructed to guide learning, and discriminative feature extraction branches are designed for channel and spatial dimensions. On the FAIR1M-OR dataset, adding only a small number of parameters can improve the performance of the baseline model by about 4.6 percentage points.

Recommended citation:
Y. Gao, C. Deng, L. Chen and Z. Zhu (corresponding author), "A Scale-Aware and Discriminative Feature Learning Network for Fine-Grained Rigid Object Recognition," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 1695-1705, 2025, doi: 10.1109/JSTARS.2024.3484411.
Download Paper

Align and Complete Samples in Remote Sensing Fine-Grained Rigid Object Detection

Published in IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2025

ACDet framework This paper proposes the ACDet rigid object fine-grained detector, which has the following core contributions: 1) adaptive anchor point alignment, decoupling classification centripetal deviation to achieve adaptive alignment; 2) Online tail sample supplementation algorithm to dynamically maintain category balance; 3) Adaptive grouping enhances discriminative features. Achieve SOTA with fewer resources.

Recommended citation:
Z. Zhu, J. Kang, W. Diao, B. Wang and J. Ni, "Align and Complete Samples in Remote Sensing Fine-Grained Rigid Object Detection," in IEEE Transactions on Geoscience and Remote Sensing, vol. 63, pp. 1-17, 2025, Art no. 5655617, doi: 10.1109/TGRS.2025.3635340.
Download Paper | Download Code

Distilling Missed Samples for Remote Sensing Oriented Object Detectors

Published in IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2026

DMR framework This paper proposes a knowledge distillation method based on missed detection sample enhancement: designing a cross scale missed detection sample enhancement dynamic selection of difficult samples, proposing local feature alignment distillation of key feature distributions, introducing generative adversarial constraint angle prediction, and improving the detection performance of lightweight detectors for multi-scale remote sensing targets in any direction.

Recommended citation:
L. He, P. Chen, B. Dong, Y. Zhang, J. Ni and Z. Zhu (corresponding author), "Distilling Missed Samples for Remote Sensing Oriented Object Detectors," in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 19, pp. 9980-9997, 2026, doi: 10.1109/JSTARS.2026.3673759.
Download Paper

talks

teaching