TopoAD: Resource-Efficient OOD Detection via Multi-Scale Euler Characteristic Curves
Open Access
- 25 January 2026
- journal article
- research article
- Published by MDPI AG in Sustainability
- Vol. 18 (3) , 1215
Abstract
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.Keywords
Funding Information
- Ministry of Education in China (25YJA880044)
- Project of Industry university-institute Cooperation in Colleges and Universities in Fujian Province (2024h6007)
- Project of Software Technology Innovation Research and Industrialization in Fujian Province (2024.488)
This publication has 10 references indexed in Scilit:
- A comprehensive review of deep neural network interpretation using topological data analysisNeurocomputing, 2024
- Topological deep learning: a review of an emerging paradigmArtificial Intelligence Review, 2024
- GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection2023
- LINe: Out-of-Distribution Detection by Leveraging Important Neurons2023
- Euler characteristic curves and profiles: a stable shape invariant for big data problemsGigaScience, 2022
- ViM: Out-Of-Distribution with Virtual-logit Matching2022
- EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover ClassificationIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
- Deep Residual Learning for Image Recognition2016
- Describing Textures in the Wild2014
- Automated Flower Classification over a Large Number of Classes2008