Liqiang Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Liqiang Lin has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Xiaolong Liu
College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, China
3 shared publications - Shuwu Chen
College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou, China
2 shared publications - Yu Lin
Key Laboratory of Smart Agriculture and Forestry, Fujian Agriculture and Forestry University, Fuzhou 350002, China
2 shared publications - Yunyu Kang
College of Computer and Information Science, Fujian Agriculture and Forestry University, Fuzhou, China
2 shared publications - Zhiyu Lin
College of Computer and Information Sciences, Fujian Agriculture and Forestry University, Fuzhou 350002, China
2 shared publications Hanbin Lin
1 shared publication
Latest Publications
- Open Access
- 25 January 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (3) , 1215
TopoAD: Resource-Efficient OOD Detection via Multi-Scale Euler Characteristic Curves
Out-of-distribution (OOD) detection is essential for ensuring the reliability of machine learning models deployed in safety-critical applications. Existing methods often rely solely on statistical properties of feature distributions while ignoring the geometric structure of learned representations. We propose TopoAD, a topology-aware OOD detection framework that leverages Euler Characteristic Curves (ECCs) extracted from intermediate convolutional activation maps and fuses them with standardized energy scores. Specifically, we employ a computationally efficient superlevel-set filtration with a local estimator to capture topological invariants, avoiding the high cost of persistent homology. Furthermore, we introduce task-adaptive aggregation strategies to effectively integrate multi-scale topological features based on the complexity of distribution shifts. We evaluate our method on CIFAR-10 against four diverse OOD benchmarks spanning far-OOD (Textures), near-OOD (SVHN), and semantic shift scenarios. Our results demonstrate that TopoAD-Gated achieves superior performance on far-OOD data with 89.98% AUROC on Textures, while the ultra-lightweight TopoAD-Linear provides an efficient alternative for near-OOD detection. Comprehensive ablation studies reveal that cross-layer gating effectively captures multi-scale topological shifts, while threshold-wise attention provides limited benefit and can degrade far-OOD performance. Our analysis demonstrates that topological features are particularly effective for detecting OOD samples with distinct structural characteristics, highlighting TopoAD’s potential as a sustainable solution for resource-constrained applications in texture analysis, medical imaging, and remote sensing.
- 25 January 2026
- Published by MDPI AG in Sustainability
- Vol. 18 (3) , 1215
Open AccessTopoAD: Resource-Efficient OOD Detection via Multi-Scale Euler Characteristic Curves
Out-of-distribution (OOD) detection is essential for ensuring the reliability of machine learning models deployed in safety-critical applications. Existing methods often rely solely on statistical properties of feature distributions while ignoring the geometric structure of learned representations. We propose TopoAD, a topology-aware OOD detection framework that leverages Euler Characteristic Curves (ECCs) extracted from intermediate convolutional activation maps and fuses them with standardized energy scores. Specifically, we employ a computationally efficient superlevel-set filtration with a local estimator to capture topological invariants, avoiding the high cost of persistent homology. Furthermore, we introduce task-adaptive aggregation strategies to effectively integrate multi-scale topological features based on the complexity of distribution shifts. We evaluate our method on CIFAR-10 against four diverse OOD benchmarks spanning far-OOD (Textures), near-OOD (SVHN), and semantic shift scenarios. Our results demonstrate that TopoAD-Gated achieves superior performance on far-OOD data with 89.98% AUROC on Textures, while the ultra-lightweight TopoAD-Linear provides an efficient alternative for near-OOD detection. Comprehensive ablation studies reveal that cross-layer gating effectively captures multi-scale topological shifts, while threshold-wise attention provides limited benefit and can degrade far-OOD performance. Our analysis demonstrates that topological features are particularly effective for detecting OOD samples with distinct structural characteristics, highlighting TopoAD’s potential as a sustainable solution for resource-constrained applications in texture analysis, medical imaging, and remote sensing.
- 1 October 2025
- Published by Springer Nature
- p. 329-341
An Adversarial Attack Method Based on Local Masking and Multi-stage Momentum Optimization
- 1 October 2025
- Published by Springer Nature
- p. 329-341
An Adversarial Attack Method Based on Local Masking and Multi-stage Momentum Optimization
- 11 August 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 260
Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models
- 11 August 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 260
Robust cross-image adversarial watermark with JPEG resistance for defending against Deepfake models
- Open Access
- 21 July 2025
- Published by MDPI AG in Information
- Vol. 16 (7) , 619
Adaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression
Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we introduce the Multi-Gradient Guided Network (MGGN), an extension of single-gradient guidance that combines gradients from several reference models. The gradients are merged through an adaptive weighting scheme, and an orthogonal-projection step is applied to reduce potential conflicts between them. Experiments on sine regression are used to evaluate the method. The results indicate that MGGN achieves higher predictive accuracy and improved stability than existing single-gradient guidance and meta-learning baselines, benefiting from the complementary information provided by multiple reference models.
- 21 July 2025
- Published by MDPI AG in Information
- Vol. 16 (7) , 619
Open AccessAdaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression
Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we introduce the Multi-Gradient Guided Network (MGGN), an extension of single-gradient guidance that combines gradients from several reference models. The gradients are merged through an adaptive weighting scheme, and an orthogonal-projection step is applied to reduce potential conflicts between them. Experiments on sine regression are used to evaluate the method. The results indicate that MGGN achieves higher predictive accuracy and improved stability than existing single-gradient guidance and meta-learning baselines, benefiting from the complementary information provided by multiple reference models.