ZZZhuangzhuang Zhou

Zhuangzhuang Zhou

*This is an algorithmically generated author record based on publicly available information.

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


Zhuangzhuang Zhou has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • CoreKD: Adaptive core-aware knowledge distillation for tiny object detection in remote sensing imagery

    by Zhuangzhuang Zhou, Weixiang Ren, Xuewu Zhao, Ning Yu, Yingying Zhu, Lingling Li

  • Open Access

    Prediction of EV Charging Pile Health Degree Based on KAN-BiLSTM-SA

    by Jiale Li, Xuewu Zhao, Jingyang Xu, Zhuangzhuang Zhou, Weixiang Ren, Shizhe Zhang

    With the rapid expansion of the EV industry, the operational health of charging piles has become a critical factor affecting charging safety and operation and maintenance (O&M) efficiency. To address the challenges posed by complex multi-source data coupling and the limited nonlinear fitting and feature extraction capabilities of traditional models in charging pile health degree prediction, this paper proposes a KAN-BiLSTM-SA-based health degree prediction method. First, the health degree is defined by taking the remaining time before fault occurrence as the core indicator, and hierarchical health levels are established accordingly. Then, a self-attention (SA) mechanism is embedded into the BiLSTM module of the KAN-BiLSTM architecture, enabling adaptive weighting of fault-sensitive temporal features and enhancing the model's ability to capture degradation patterns preceding failures. Experimental results based on real-world operation and maintenance data demonstrate that the proposed method achieves superior prediction accuracy and stability compared with several representative baseline models. Furthermore, simulation-based engineering validation confirms that an operation and maintenance strategy guided by the proposed model can effectively support preventive maintenance and provide decision-making references for intelligent charging pile management.

  • GenDist: Generative-Driven Knowledge Distillation for Small Object Detection in Remote Sensing Images

    by Zhuangzhuang Zhou, Xuewu Zhao, Xuezhuan Zhao, Yingying Zhu, Zunjin Zhao, Lingling Li

    Optimal efficiency is always the primary pursuit of the remote sensing community. However, the blurred appearance in small objects causes increasingly deeper and wider detectors, posing a significant challenge for deployment. Knowledge Distillation (KD), which can shorten the time from image acquisition to interpretation, has become a hotspot. In this paper, contrary to traditional feature imitation methods, we propose generative-driven knowledge distillation for small object detection (GenDist), which reconstructs teacher-like representations from the partially masked student features to achieve knowledge transfer. Masking during training strengthens the student’s ability to generalize in complex scenes. Specifically, GenDist contains three parts: Online Self-Correct Mask (O-SCM), Dynamic Activation Global Context (DAGC) and Sampling-Aligned Generation (SAG). First, O-SCM is utilized to identify informative masking regions that guide the student to reconstruct the teacher-like features. By integrating an online self-correction mechanism, it adaptively directs generative supervision toward regions that are ignored or misinterpreted by students. Then, DAGC refines teacher features via global context modeling and critical feature selection, facilitating more accurate object detail capture by the student model. Finally, SAG improves the quality of feature reconstruction by introducing the learnable offset sampling, enabling students to learn irregular areas such as the small instances’ edges and texture transitions. Our proposed method finds the sweet spot between precision and speed in an elegant way. GenDist yields stable performance gains for student models across the DIOR, AI-TOD, SODA-D, and SSDD datasets. For the lightweight detectors, it cuts the model’s parameter count by roughly 38.2%, while keeping accuracy loss under 3.9%.


  • KLDet: Detecting Tiny Objects in Remote Sensing Images via Kullback–Leibler Divergence

    by Zhuangzhuang Zhou, Yingying Zhu

    Remote sensing images (RSIs) frequently contain quite a few tiny objects with a finite number of pixels to study. The limited spatial information poses a challenge for extracting discriminative features for representing the characteristics of tiny objects. Existing solutions mainly focus on aggregating contextual information at different levels, while rarely touching the step that is crucial for model training, i.e., label assignment. Tiny instances occupy fairly small regions of images and have limited overlaps to priors (anchors or dots), which is a dilemma for traditional label assignment strategies. Despite being simple and effective, the mainstream IoU-based (Intersection over Union) label assignment strategy struggles to accurately measure the localization of tiny bounding boxes. In contrast, the Kullback-Leibler Divergence (KLD) localization metric accurately reflects minor offsets of tiny bounding boxes. More importantly, KLD is able to measure non-overlapping bounding boxes, providing an advantage in mining more potential positive samples of tiny objects. In this paper, from a cost-efficient point of view, we detect tiny objects through KLD in the form of single-stage framework. Specifically, we model the parameterized Bounding box as a two-dimensional Gaussian distribution (Bbox2Gaussian) in order to use KLD as a localization metric. Then, we propose an adaptive online training sample mining strategy (Ali-TSM) based on inter-distribution similarity, which selects high-quality positive samples by considering localization and classification rather than just centroid distance or IoU. Finally, task-level attention (TlA) is introduced to guide the model in freely selecting the appropriate features for the classification or regression task. We conducted extensive experiments on four popular public datasets. Compared to the baseline, KLDet improves performance on AI-TOD (Tiny Object Detection in Aerial Images) and DIOR (object DetectIon in Optical Remote sensing image) by 4.1 AP and 6.7 mAP. On VisDrone and SODA-D (Small Object Detection dAtasets), KLDet exhibits superior performance than baseline. The code is available at https://github.com/TinyOD/mmdet-kldet.


  • RaFPN: Relation-Aware Feature Pyramid Network for Dense Image Prediction

    by Zhuangzhuang Zhou, Yingying Zhu

    Intuitively, relations among objects assist a model in performing inference under constrained environments. However, the top-down information flow in the Feature pyramid network (FPN) dilutes the relation features contained in the non-adjacent layers. Such a defect reduces the accuracy of detectors, especially for small or obscured objects. To adequately exploit the relations among object instances, we propose the relation-aware feature pyramid network (RaFPN), a simple but effective balanced multi-scale feature module for dense image prediction. RaFPN models the relations among objects by computing the similarity between pixels located on cross-scale features. The result is then delivered to FPN to guide the detector in completing accurate inference. Specifically, we first generate a pair of cross-scale aggregated features based on the channel importance of the output features from FPN. After that, the relation among the cross-scale objects is extracted by a bi-directional interaction mechanism. Finally, relation features are injected directly into each layer of the feature pyramid to avoid dilution. In this way, the relation among instances can adequately guide the detector for dense prediction. Our RaFPN pushes the performance bound of Faster RCNN by 2.0 AP (average precision), outperforming the recent state-of-the-art FPN-based improvements. Notably, for dense prediction tasks such as instance, semantic, and panoptic segmentation, our method brings consistent boosts to them as well.