Can Gao

Dr. Can Gao

College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2025 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
HLHanzhe Liang
Hanzhe Liang
GXGuoyang Xie
Guoyang Xie
CHChengbin Hou
Chengbin Hou
Bingshu WangBingshu Wang
Bingshu Wang
Can GaoCan Gao
Can Gao
Jinbao WangJinbao Wang
Jinbao Wang
3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we observed this prototype is straightforward and effective. As a result, we introduce a newly designed mode named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction method for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further precise spatial structure aligning. Extensive experiments validate the efficiency of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and verified in both classification and segmentation tasks. Our code will be released upon acceptance.

18 May 2023 in Systems
Verified
Journal Article
Open access
PDF file
KLKuan Li
Kuan Li
QLQianzhi Lian
Qianzhi Lian
Can GaoCan Gao
Can Gao
FZFuyong Zhang
Fuyong Zhang
Data-driven decision-making is the process of using data to inform your decision-making process and validate a course of action before committing to it. The quality of unlabeled data in real-world scenarios presents challenges for semi-supervised learning. Effectively leveraging unlabeled data for learning is challenging due to the need for labeled information, while the scarcity of labeled data requires efficient and flexible data augmentation methods. To address these challenges, this paper proposes the AatMatch algorithm, which uses a momentum model, coarse learning, and adversarial training to generate adversarial examples for different classes. The algorithm sets the threshold for generating pseudo-labels and reinforces the results with adversarial perturbations based on evaluation results. In addition, a more refined learning strategy for unlabeled data is adjusted by setting adaptive weights based on the confidence of each unlabeled data point, thereby mitigating the adverse effects of low-confidence unlabeled data on the model. Experimental evaluations on several datasets, including CIFAR-10, CIFAR-100, and SVHN, demonstrate the effectiveness of the proposed AatMatch algorithm in semi-supervised learning. Specifically, the algorithm achieves the lowest error rates for multiple scenarios on these datasets.

4 March 2025 in arXiv
Verified
Preprint
Open access
PDF file
HLHanzhe Liang
Hanzhe Liang
JZJie Zhou
Jie Zhou
XCXuanxin Chen
Xuanxin Chen
TDTao Dai
Tao Dai
Jinbao WangJinbao Wang
Jinbao Wang
Can GaoCan Gao
Can Gao
3D anomaly detection (AD) is prominent but difficult due to lacking a unified theoretical foundation for preprocessing design. We establish the Fence Theorem, formalizing preprocessing as a dual-objective semantic isolator: (1) mitigating cross-semantic interference to the greatest extent feasible and (2) confining anomaly judgments to aligned semantic spaces wherever viable, thereby establishing intra-semantic comparability. Any preprocessing approach achieves this goal through a two-stage process of Emantic-Division and Spatial-Constraints stage. Through systematic deconstruction, we theoretically and experimentally subsume existing preprocessing methods under this theorem via tripartite evidence: qualitative analyses, quantitative studies, and mathematical proofs. Guided by the Fence Theorem, we implement Patch3D, consisting of Patch-Cutting and Patch-Matching modules, to segment semantic spaces and consolidate similar ones while independently modeling normal features within each space. Experiments on Anomaly-ShapeNet and Real3D-AD with different settings demonstrate that progressively finer-grained semantic alignment in preprocessing directly enhances point-level AD accuracy, providing inverse validation of the theorem's causal logic.