Research map / Label-efficient and robust learning / Test-time adaptation
Topology-Aware Optimal Transport for Source-Free Test-Time Adaptation in Anomaly Segmentation
Ali Zia, Usman Ali, Abdelwahed Khamis, Muhammad Umer Ramzan, Abdul Rehman, Wei Xiang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a topology-aware optimal transport approach for source-free test-time adaptation in anomaly segmentation, using deep topological data analysis to characterise anomalies as disruptions to global structure.
Problem
Anomaly segmentation under test-time distribution shift, where threshold-based binarisation yields brittle masks.
Approach
Uses deep topological data analysis (persistent structural invariants such as connectivity and cycles) combined with optimal transport to characterise anomalies as disruptions to global structure rather than local thresholds, applied in a source-free test-time adaptation setting.
Closest papers by meaning
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (ICLR 2025 · similarity 0.85)
- TopoDiffusionNet: A Topology-aware Diffusion Model (ICLR 2025 · similarity 0.84)
- FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis (NeurIPS 2025 · similarity 0.84)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.84)
- ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection (NeurIPS 2025 · similarity 0.84)
- Topological Periodicity Test (TopPT) via Confidence Bound of Time-Delay Embeddings (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
