Zheng Qin
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
Research Subjects
Zheng Qin has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Hao Yu
Technical University of Munich, Mnchen, Germany
5 shared publications - Kai Xu
Institute of AI for Industries, Chinese Academy of Sciences, Nanjing, China
3 shared publications - Yuxing Peng
National University of Defense Technology Changsha China
3 shared publications - Benjamin Busam
Technical University of Munich
2 shared publications Changjian Wang
2 shared publications- Chenyang Zhu
National University of Defense Technology
2 shared publications
Latest Publications
- Open Access
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 651-658
Density-aware and Cluster-based Federated Anomaly Detection on Data Streams
Federated active anomaly detection on data streams becomes a crucial research problem, since it attempts to discover anomalous data with protecting data privacy and avoiding extensive data labeling. Although extensive work has been conducted on anomaly detection, distinguishing similar anomalies of different categories still remains quite a challenging issue. The requirement of privacy protection in federated settings aggravates the difficulties for instance query and scoring in active anomaly detection when solving this issue. To the best of our knowledge, limited work has focused on this research area. Therefore, we propose Density-aware and cluster-based Federated Active anomaly detection on data Streams, called DFAS. We design a novel lightweight federated anomaly detection clusters with density-aware hash cells, which successfully capture evolving data distribution. The federated anomaly detection clusters are incrementally updated with an acceptable theoretical reconstruction error guarantee. In addition, we propose a straightforward but effective metric divergences accompanied by a greedy search algorithm, which takes both global aggregation bias mitigation and efficiency into account. At last, DFAS detects anomalies and queries the instances for manual labels by measuring the density in hash cells of each cluster, effectively distinguishing closely distributed anomaly classes while maintaining data privacy in the federated setting. Comprehensive experiments on several real-world data sets show that DFAS outperforms previous methods, improving F1 scores by up to 26.7%.
- 10 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 651-658
Open AccessDensity-aware and Cluster-based Federated Anomaly Detection on Data Streams
Federated active anomaly detection on data streams becomes a crucial research problem, since it attempts to discover anomalous data with protecting data privacy and avoiding extensive data labeling. Although extensive work has been conducted on anomaly detection, distinguishing similar anomalies of different categories still remains quite a challenging issue. The requirement of privacy protection in federated settings aggravates the difficulties for instance query and scoring in active anomaly detection when solving this issue. To the best of our knowledge, limited work has focused on this research area. Therefore, we propose Density-aware and cluster-based Federated Active anomaly detection on data Streams, called DFAS. We design a novel lightweight federated anomaly detection clusters with density-aware hash cells, which successfully capture evolving data distribution. The federated anomaly detection clusters are incrementally updated with an acceptable theoretical reconstruction error guarantee. In addition, we propose a straightforward but effective metric divergences accompanied by a greedy search algorithm, which takes both global aggregation bias mitigation and efficiency into account. At last, DFAS detects anomalies and queries the instances for manual labels by measuring the density in hash cells of each cluster, effectively distinguishing closely distributed anomaly classes while maintaining data privacy in the federated setting. Comprehensive experiments on several real-world data sets show that DFAS outperforms previous methods, improving F1 scores by up to 26.7%.
- 3 November 2024
- Published by Springer Nature
- p. 172-186
Instance-Level Scaling and Dynamic Margin-Alignment Knowledge Distillation
- 3 November 2024
- Published by Springer Nature
- p. 172-186
Instance-Level Scaling and Dynamic Margin-Alignment Knowledge Distillation
- Open Access
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 309-330
Learning accurate template matching with differentiable coarse-to-fine correspondence refinement
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 309-330
Open AccessLearning accurate template matching with differentiable coarse-to-fine correspondence refinement
Template matching is a fundamental task in computer vision and has been studied for decades. It plays an essential role in manufacturing industry for estimating the poses of different parts, facilitating downstream tasks such as robotic grasping. Existing methods fail when the template and source images have different modalities, cluttered backgrounds, or weak textures. They also rarely consider geometric transformations via homographies, which commonly exist even for planar industrial parts. To tackle the challenges, we propose an accurate template matching method based on differentiable coarse-to-fine correspondence refinement. We use an edge-aware module to overcome the domain gap between the mask template and the grayscale image, allowing robust matching. An initial warp is estimated using coarse correspondences based on novel structure-aware information provided by transformers. This initial alignment is passed to a refinement network using references and aligned images to obtain sub-pixel level correspondences which are used to give the final geometric transformation. Extensive evaluation shows that our method to be significantly better than state-of-the-art methods and baselines, providing good generalization ability and visually plausible results even on unseen real data.
- Top Cited Papers
- 3 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (5) , 3796-3812
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8${}^\circ$ in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.- 3 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (5) , 3796-3812
Top Cited PapersRIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8${}^\circ$ in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch. - 10 November 2023
- Published by Springer Nature
- p. 165-176
Reduced-Resolution Head for Object Detection
- 19 May 2023
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 104
CasViGE: Learning robust point cloud registration with cascaded visual-geometric encoding
- 19 May 2023
- Published by Elsevier in Computer Aided Geometric Design
- Vol. 104
CasViGE: Learning robust point cloud registration with cascaded visual-geometric encoding
- Top Cited Papers
- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9806-9821
GeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by$18{\sim }31$ percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark.- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (8) , 9806-9821
Top Cited PapersGeoTransformer: Fast and Robust Point Cloud Registration With Geometric Transformer
We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of repeatable keypoints which is difficult to do especially in low-overlap scenarios. They seek correspondences over downsampled superpoints, which are then propagated to dense points. Superpoints are matched based on whether their neighboring patches overlap. Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds. We propose Geometric Transformer, or GeoTransformer for short, to learn geometric feature for robust superpoint matching. It encodes pair-wise distances and triplet-wise angles, making it invariant to rigid transformation and robust in low-overlap cases. The simplistic design attains surprisingly high matching accuracy such that no RANSAC is required in the estimation of alignment transformation, leading to 100 times acceleration. Extensive experiments on rich benchmarks encompassing indoor, outdoor, synthetic, multiway and non-rigid demonstrate the efficacy of GeoTransformer. Notably, our method improves the inlier ratio by$18{\sim }31$ percentage points and the registration recall by over 7 points on the challenging 3DLoMatch benchmark. - Open Access
Task-Specific Context Decoupling for Object Detection
Classification and localization are two main sub-tasks in object detection. Nonetheless, these two tasks have inconsistent preferences for feature context, i.e., localization expects more boundary-aware features to accurately regress the bounding box, while more semantic context is preferred for object classification. Exsiting methods usually leverage disentangled heads to learn different feature context for each task. However, the heads are still applied on the same input features, which leads to an imperfect balance between classifcation and localization. In this work, we propose a novel Task-Specific COntext DEcoupling (TSCODE) head which further disentangles the feature encoding for two tasks. For classification, we generate spatially-coarse but semantically-strong feature encoding. For localization, we provide high-resolution feature map containing more edge information to better regress object boundaries. TSCODE is plug-and-play and can be easily incorperated into existing detection pipelines. Extensive experiments demonstrate that our method stably improves different detectors by over 1.0 AP with less computational cost. Our code and models will be publicly released.
Open AccessTask-Specific Context Decoupling for Object Detection
Classification and localization are two main sub-tasks in object detection. Nonetheless, these two tasks have inconsistent preferences for feature context, i.e., localization expects more boundary-aware features to accurately regress the bounding box, while more semantic context is preferred for object classification. Exsiting methods usually leverage disentangled heads to learn different feature context for each task. However, the heads are still applied on the same input features, which leads to an imperfect balance between classifcation and localization. In this work, we propose a novel Task-Specific COntext DEcoupling (TSCODE) head which further disentangles the feature encoding for two tasks. For classification, we generate spatially-coarse but semantically-strong feature encoding. For localization, we provide high-resolution feature map containing more edge information to better regress object boundaries. TSCODE is plug-and-play and can be easily incorperated into existing detection pipelines. Extensive experiments demonstrate that our method stably improves different detectors by over 1.0 AP with less computational cost. Our code and models will be publicly released.
- Open Access
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8\degree in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.
Open AccessRIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8\degree in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.