Zhikang Zou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhikang Zou has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Xiang Bai
Huazhong University of Science and Technology, Wuhan, China
4 shared publications - Xiao Tan
Department of Computer Vision Technology (VIS), Baidu Inc., Beijing, China
4 shared publications - Xiaoqing Ye
Wuhan University, Wuhan, China
4 shared publications - Dingkang Liang
Huazhong University of Science and Technology
3 shared publications - Zhe Liu
Huazhong University of Science and Technology
2 shared publications Chunsheng Shi
School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
1 shared publication
Latest Publications
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (1) , 840-858
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving oriented objects common in aerial images unexplored. At the same time, the annotation cost of oriented objects is significantly higher than that of their horizontal counterparts (an approximate 36.5% increase in costs). Therefore, in this paper, we propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++. Specifically, we observe that objects from aerial images usually have arbitrary orientations, small scales, and dense distribution, which inspires the following core designs: a Simple Instance-aware Dense Sampling (SIDS) strategy is used to generate comprehensive dense pseudo-labels; the Geometry-aware Adaptive Weighting (GAW) loss dynamically modulates the importance of each pair between pseudo-label and corresponding prediction by leveraging the intricate geometric information of aerial objects; we treat aerial images as global layouts and explicitly build the many-to-many relationship between the sets of pseudo-labels and predictions via the proposed Noise-driven Global Consistency (NGC). Extensive experiments conducted on various oriented object datasets under various labeled settings demonstrate the effectiveness of our method. For example, on the DOTA-V2.0/DOTA-V1.5 benchmark, the proposed method outperforms previous state-of-the-art (SOTA) by a large margin (+2.90/2.14, +2.16/2.18, and +2.66/2.32) mAP under 10%, 20%, and 30% labeled data settings, respectively, with single-scale training and testing. More importantly, it still improves upon a strong supervised baseline with 70.66 mAP, trained using the full DOTA-V1.5 train-val set, by +1.82 mAP, resulting in a 72.48 mAP, pushing the new state-of-the-art. Moreover, our method demonstrates stable generalization ability across different oriented detectors, even for multi-view oriented 3D object detectors.
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (1) , 840-858
SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection
Semi-supervised object detection (SSOD), leveraging unlabeled data to boost object detectors, has become a hot topic recently. However, existing SSOD approaches mainly focus on horizontal objects, leaving oriented objects common in aerial images unexplored. At the same time, the annotation cost of oriented objects is significantly higher than that of their horizontal counterparts (an approximate 36.5% increase in costs). Therefore, in this paper, we propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++. Specifically, we observe that objects from aerial images usually have arbitrary orientations, small scales, and dense distribution, which inspires the following core designs: a Simple Instance-aware Dense Sampling (SIDS) strategy is used to generate comprehensive dense pseudo-labels; the Geometry-aware Adaptive Weighting (GAW) loss dynamically modulates the importance of each pair between pseudo-label and corresponding prediction by leveraging the intricate geometric information of aerial objects; we treat aerial images as global layouts and explicitly build the many-to-many relationship between the sets of pseudo-labels and predictions via the proposed Noise-driven Global Consistency (NGC). Extensive experiments conducted on various oriented object datasets under various labeled settings demonstrate the effectiveness of our method. For example, on the DOTA-V2.0/DOTA-V1.5 benchmark, the proposed method outperforms previous state-of-the-art (SOTA) by a large margin (+2.90/2.14, +2.16/2.18, and +2.66/2.32) mAP under 10%, 20%, and 30% labeled data settings, respectively, with single-scale training and testing. More importantly, it still improves upon a strong supervised baseline with 70.66 mAP, trained using the full DOTA-V1.5 train-val set, by +1.82 mAP, resulting in a 72.48 mAP, pushing the new state-of-the-art. Moreover, our method demonstrates stable generalization ability across different oriented detectors, even for multi-view oriented 3D object detectors.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 7230-7242
Coupling and Decoupling: Towards Temporal Feedback for 3D Object Detection
3D object detection has garnered significant attention within the academic community, primarily due to its broad utility in domains such as autonomous driving and robotics. Prior research efforts have predominantly concentrated on leveraging temporal contextual information embedded within sequential data to enhance the current feature representations. However, a notable limitation of these endeavors lies in their inadequate treatment of the inherent noise present within historical sequences, thereby constraining the efficiency of fusion methods. In this paper, we propose a new temporal feedback network, named TFNet, to model and correct the temporal noise by designing a coupling-decoupling mechanism. Central to our approach are two distinct modules: (i) Foreground Feature Enhancement, which amplifies sparse instance details across temporal frames, thereby furnishing essential local information priors for subsequent fusion; and (ii) Coupling-Decoupling Feature Interaction, designed to first aggregate temporal contextual information and then disentangle fusion features into frame-specific representations. Leveraging a feedback strategy, this module can adaptively enhance useful information and eliminate noise within individual frame features. Empirical evaluations conducted on the nuScenes benchmark demonstrate the effectiveness of TFNet, achieving the new state-of-the-art performance without any bells and whistles.
- 14 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 7230-7242
Coupling and Decoupling: Towards Temporal Feedback for 3D Object Detection
3D object detection has garnered significant attention within the academic community, primarily due to its broad utility in domains such as autonomous driving and robotics. Prior research efforts have predominantly concentrated on leveraging temporal contextual information embedded within sequential data to enhance the current feature representations. However, a notable limitation of these endeavors lies in their inadequate treatment of the inherent noise present within historical sequences, thereby constraining the efficiency of fusion methods. In this paper, we propose a new temporal feedback network, named TFNet, to model and correct the temporal noise by designing a coupling-decoupling mechanism. Central to our approach are two distinct modules: (i) Foreground Feature Enhancement, which amplifies sparse instance details across temporal frames, thereby furnishing essential local information priors for subsequent fusion; and (ii) Coupling-Decoupling Feature Interaction, designed to first aggregate temporal contextual information and then disentangle fusion features into frame-specific representations. Leveraging a feedback strategy, this module can adaptively enhance useful information and eliminate noise within individual frame features. Empirical evaluations conducted on the nuScenes benchmark demonstrate the effectiveness of TFNet, achieving the new state-of-the-art performance without any bells and whistles.
- Top Cited Papers
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10949-10966
Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on downstream tasks, which is storage-intensive and computationally demanding. To address this issue, we propose a novel Parameter-Efficient Fine-Tuning (PEFT) method for point cloud, called PointGST (Point cloud Graph Spectral Tuning). PointGST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) for fine-tuning parameters in the spectral domain. The core idea is built on two observations: 1) The inner tokens from frozen models might present confusion in the spatial domain; 2) Task-specific intrinsic information is important for transferring the general knowledge to the downstream task. Specifically, PointGST transfers the point tokens from the spatial domain to the spectral domain, effectively de-correlating confusion among tokens by using orthogonal components for separation. Moreover, the generated spectral basis involves intrinsic information about the downstream point clouds, enabling more targeted tuning. As a result, PointGST facilitates the efficient transfer of general knowledge to downstream tasks while significantly reducing training costs. Extensive experiments on challenging point cloud datasets across various tasks demonstrate that PointGST not only outperforms its fully fine-tuning counterpart but also significantly reduces trainable parameters, making it a promising solution for efficient point cloud learning. Moreover, it achieves superior accuracies of 99.48%, 97.76%, and 96.18% on the ScanObjNN OBJ_BG, OBJ_ONLY, and PB_T50_RS datasets, respectively, establishing a new state-of-the-art, while using only 0.67% of the trainable parameters.
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 47 (12) , 10949-10966
Top Cited PapersParameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learning
Recently, leveraging pre-training techniques to enhance point cloud models has become a prominent research topic. However, existing approaches typically require full fine-tuning of pre-trained models to achieve satisfactory performance on downstream tasks, which is storage-intensive and computationally demanding. To address this issue, we propose a novel Parameter-Efficient Fine-Tuning (PEFT) method for point cloud, called PointGST (Point cloud Graph Spectral Tuning). PointGST freezes the pre-trained model and introduces a lightweight, trainable Point Cloud Spectral Adapter (PCSA) for fine-tuning parameters in the spectral domain. The core idea is built on two observations: 1) The inner tokens from frozen models might present confusion in the spatial domain; 2) Task-specific intrinsic information is important for transferring the general knowledge to the downstream task. Specifically, PointGST transfers the point tokens from the spatial domain to the spectral domain, effectively de-correlating confusion among tokens by using orthogonal components for separation. Moreover, the generated spectral basis involves intrinsic information about the downstream point clouds, enabling more targeted tuning. As a result, PointGST facilitates the efficient transfer of general knowledge to downstream tasks while significantly reducing training costs. Extensive experiments on challenging point cloud datasets across various tasks demonstrate that PointGST not only outperforms its fully fine-tuning counterpart but also significantly reduces trainable parameters, making it a promising solution for efficient point cloud learning. Moreover, it achieves superior accuracies of 99.48%, 97.76%, and 96.18% on the ScanObjNN OBJ_BG, OBJ_ONLY, and PB_T50_RS datasets, respectively, establishing a new state-of-the-art, while using only 0.67% of the trainable parameters.
- 30 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (3) , 3071-3083
An Empirical Study of Ground Segmentation for 3-D Object Detection
The ratio of foreground and background points directly impacts the accuracy and speed of the lidar-based 3D object detection methods. However, existing methods generally ignore the impact of ground points. Although some traditional ground segmentation algorithms are available to remove ground point clouds, they usually suffer from over-segmentation, which leads to a sub-optimal and even worse performance for the downstream 3D detection task. We conduct an in-depth analysis and attribute this phenomenon to the reason that some crucial foreground points attached to the ground (e.g., the wheels of Cars, or the feet of Pedestrians) are directly removed due to over-segmentation. To this end, we propose a new Attached Point Restoring (APR) module to recover these discarded foreground points. Experimental results demonstrate the effectiveness and generalization of APR by integrating it into various ground segmentation algorithms to boost the performance or the running time of 3D detection on KITTI and Waymo datasets. Finally, we hope this paper can serve as a new guide to inspire future research in this field. Code is available at https://github.com/yhc2021/GPR.
- 30 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (3) , 3071-3083
An Empirical Study of Ground Segmentation for 3-D Object Detection
The ratio of foreground and background points directly impacts the accuracy and speed of the lidar-based 3D object detection methods. However, existing methods generally ignore the impact of ground points. Although some traditional ground segmentation algorithms are available to remove ground point clouds, they usually suffer from over-segmentation, which leads to a sub-optimal and even worse performance for the downstream 3D detection task. We conduct an in-depth analysis and attribute this phenomenon to the reason that some crucial foreground points attached to the ground (e.g., the wheels of Cars, or the feet of Pedestrians) are directly removed due to over-segmentation. To this end, we propose a new Attached Point Restoring (APR) module to recover these discarded foreground points. Experimental results demonstrate the effectiveness and generalization of APR by integrating it into various ground segmentation algorithms to boost the performance or the running time of 3D detection on KITTI and Waymo datasets. Finally, we hope this paper can serve as a new guide to inspire future research in this field. Code is available at https://github.com/yhc2021/GPR.
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19917-19928
Multi-Modal 3D Object Detection by Box Matching
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detection rely on an accurate alignment and calibration between 3D point clouds and RGB images. However, such an assumption is not reliable in a real-world self-driving system, as the alignment between different modalities is easily affected by asynchronous sensors and disturbed sensor placement. We propose a novel F usion network by B ox M atching ( FBMNet ) for multi-modal 3D detection, which provides an alternative way for cross-modal feature alignment by learning the correspondence at the bounding box level to free up the dependency of calibration during inference. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combining their ROI features. Extensive experiments on the nuScenes dataset demonstrate that our method is much more robust in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods. We hope that our could provide an available solution to dealing with these challenging cases for safety in real autonomous driving scenarios.
- 17 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19917-19928
Multi-Modal 3D Object Detection by Box Matching
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detection rely on an accurate alignment and calibration between 3D point clouds and RGB images. However, such an assumption is not reliable in a real-world self-driving system, as the alignment between different modalities is easily affected by asynchronous sensors and disturbed sensor placement. We propose a novel F usion network by B ox M atching ( FBMNet ) for multi-modal 3D detection, which provides an alternative way for cross-modal feature alignment by learning the correspondence at the bounding box level to free up the dependency of calibration during inference. With the learned assignments between 3D and 2D object proposals, the fusion for detection can be effectively performed by combining their ROI features. Extensive experiments on the nuScenes dataset demonstrate that our method is much more robust in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods. We hope that our could provide an available solution to dealing with these challenging cases for safety in real autonomous driving scenarios.
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 10478-10485
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property, which is a critical lack of depth information in the 2D image plane. While existing approaches leverage off-the-shelf depth estimation or rely on LiDAR sensors to mitigate this problem, dependence on the additional depth model or expensive equipment severely limits their scalability to generic 3D perception. In this paper, we propose a stereo-guided monocular 3D object detection framework, dubbed SGM3D, which aligns the monocular feature to the stereo feature and exploits the network's ability of generating the cross-modal feature for accurate 3D object detection. We present a multi-granularity feature alignment (MG-FA) mechanism to exploit the network's ability to generate stereo-mimicking features given only monocular cues. Coarse feature-level, as well as fine anchor-level feature alignment, are both leveraged for monocular feature guidance. In addition, we introduce an IoU matching-based feature alignment (IoU-MA) method for object-level feature alignment between the stereo and monocular predictions to alleviate the mismatches while adopting the MG-FA. Extensive experiments on the KITTI datasets demonstrate the effectiveness of our method. Code is publicly available at https://github.com/zhouzheyuan/sgm3d .
- 18 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (4) , 10478-10485
SGM3D: Stereo Guided Monocular 3D Object Detection
Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property, which is a critical lack of depth information in the 2D image plane. While existing approaches leverage off-the-shelf depth estimation or rely on LiDAR sensors to mitigate this problem, dependence on the additional depth model or expensive equipment severely limits their scalability to generic 3D perception. In this paper, we propose a stereo-guided monocular 3D object detection framework, dubbed SGM3D, which aligns the monocular feature to the stereo feature and exploits the network's ability of generating the cross-modal feature for accurate 3D object detection. We present a multi-granularity feature alignment (MG-FA) mechanism to exploit the network's ability to generate stereo-mimicking features given only monocular cues. Coarse feature-level, as well as fine anchor-level feature alignment, are both leveraged for monocular feature guidance. In addition, we introduce an IoU matching-based feature alignment (IoU-MA) method for object-level feature alignment between the stereo and monocular predictions to alleviate the mismatches while adopting the MG-FA. Extensive experiments on the KITTI datasets demonstrate the effectiveness of our method. Code is publicly available at https://github.com/zhouzheyuan/sgm3d .
- Open Access
DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolutional operation to aggregate long-range temporal information among adjacent snippets adaptively. The DSA module is an efficient plug-and-play module and can be combined with the off-the-shelf clip-based models (i.e., TSM, I3D) to perform powerful long-range modeling with minimal overhead. The final video architecture, coined as DSANet. We conduct extensive experiments on several video recognition benchmarks (i.e., Mini-Kinetics-200, Kinetics-400, Something-Something V1 and ActivityNet) to show its superiority. Our proposed DSA module is shown to benefit various video recognition models significantly. For example, equipped with DSA modules, the top-1 accuracy of I3D ResNet-50 is improved from 74.9% to 78.2% on Kinetics-400. Codes are available at https://github.com/whwu95/DSANet.
Open AccessDSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to yield the final video-level prediction. Thus, their video-level prediction does not consider spatio-temporal features of how video evolves along the temporal dimension. In this paper, we introduce a novel Dynamic Segment Aggregation (DSA) module to capture relationship among snippets. To be more specific, we attempt to generate a dynamic kernel for a convolutional operation to aggregate long-range temporal information among adjacent snippets adaptively. The DSA module is an efficient plug-and-play module and can be combined with the off-the-shelf clip-based models (i.e., TSM, I3D) to perform powerful long-range modeling with minimal overhead. The final video architecture, coined as DSANet. We conduct extensive experiments on several video recognition benchmarks (i.e., Mini-Kinetics-200, Kinetics-400, Something-Something V1 and ActivityNet) to show its superiority. Our proposed DSA module is shown to benefit various video recognition models significantly. For example, equipped with DSA modules, the top-1 accuracy of I3D ResNet-50 is improved from 74.9% to 78.2% on Kinetics-400. Codes are available at https://github.com/whwu95/DSANet.
- Open Access
Crowd Counting via Hierarchical Scale Recalibration Network
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenation of multi-scale information to tackle it, while the scale shifts between the feature maps are ignored. In this paper, we propose a novel Hierarchical Scale Recalibration Network (HSRNet), which addresses the above issues by modeling rich contextual dependencies and recalibrating multiple scale-associated information. Specifically, a Scale Focus Module (SFM) first integrates global context into local features by modeling the semantic inter-dependencies along channel and spatial dimensions sequentially. In order to reallocate channel-wise feature responses, a Scale Recalibration Module (SRM) adopts a step-by-step fusion to generate final density maps. Furthermore, we propose a novel Scale Consistency loss to constrain that the scale-associated outputs are coherent with groundtruth of different scales. With the proposed modules, our approach can ignore various noises selectively and focus on appropriate crowd scales automatically. Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches. More remarkably, we extend experiments on an extra vehicle dataset, whose results indicate that the proposed model is generalized to other applications.
Open AccessCrowd Counting via Hierarchical Scale Recalibration Network
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenation of multi-scale information to tackle it, while the scale shifts between the feature maps are ignored. In this paper, we propose a novel Hierarchical Scale Recalibration Network (HSRNet), which addresses the above issues by modeling rich contextual dependencies and recalibrating multiple scale-associated information. Specifically, a Scale Focus Module (SFM) first integrates global context into local features by modeling the semantic inter-dependencies along channel and spatial dimensions sequentially. In order to reallocate channel-wise feature responses, a Scale Recalibration Module (SRM) adopts a step-by-step fusion to generate final density maps. Furthermore, we propose a novel Scale Consistency loss to constrain that the scale-associated outputs are coherent with groundtruth of different scales. With the proposed modules, our approach can ignore various noises selectively and focus on appropriate crowd scales automatically. Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches. More remarkably, we extend experiments on an extra vehicle dataset, whose results indicate that the proposed model is generalized to other applications.
- 1 November 2019
- Published by Elsevier in Neurocomputing
- Vol. 367, 75-83
Attend to count: Crowd counting with adaptive capacity multi-scale CNNs
- 1 November 2019
- Published by Elsevier in Neurocomputing
- Vol. 367, 75-83
Attend to count: Crowd counting with adaptive capacity multi-scale CNNs