Research map / Label-efficient and robust learning / OOD and anomaly detection
Quantum Conflict Measurement in Decision Fusion for Out-of-Distribution Detection
Yilin Dong, T. Zhu, Xinde Li, Jean Dezert, Ri‐Gui Zhou, Changming Zhu, Lei Cao, Shuzhi Sam Ge
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fuse C-DDS with DML scores via QCI-based conflict fusion (C-DDS+) (ablation) | C-DDS · OOD detection, VGG16 average | AUC: 92.19% -> 93.58% | Improved |
| fuse C-DDS with DML scores via QCI-based conflict fusion (C-DDS+) | C-DDS · OOD detection, VGG16 average | FPR95: 30.51% -> 26.2% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, WideResNet50-2 average | AUC: 96.79% -> 97.56% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, WideResNet50-2 average | FPR95: 13% -> 11.07% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, ViT-B-16 average | AUC: 96.58% -> 97.02% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, ViT-B-16 average | FPR95: 14.04% -> 13.31% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, Swin-B average | AUC: 97.46% -> 98.07% | Improved |
| fuse C-DDS with DML scores (C-DDS+) (ablation) | C-DDS · OOD detection, Swin-B average | FPR95: 9.61% -> 8.26% | Improved |
| use C-DDS instead of DML alone on VGG16 (ablation) | DML · OOD detection, VGG16 Places FPR95 | FPR95: 32.93% -> 39.26% | Hurt |
| replace Swin-B baseline DML with C-DDS | DML · OOD detection, Swin-B average | FPR95: 35.59% -> 9.61% | Improved |
| increase number of retained common features (ablation) | C-DDS · iNaturalist and ImageNet-O, VGG | AUC | Hurt |
| increase number of retained common features (ablation) | C-DDS · Sun and Places, VGG | AUC | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Mahalanobis — Mahalanobis++: Improving OOD Detection via Feature Normalization (ICML 2025) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Qsco: A Quantum Scoring Module for Open-Set Supervised Anomaly Detection (AAAI 2025 · similarity 0.83)
- Limitations of measure-first protocols in quantum machine learning (ICML 2025 · similarity 0.79)
- QEM-Bench: Benchmarking Learning-based Quantum Error Mitigation and QEMFormer as a Multi-ranged Context Learning Baseline (ICML 2025 · similarity 0.78)
- Hybrid Quantum-Classical Multi-Agent Pathfinding (ICML 2025 · similarity 0.78)
- Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm (NeurIPS 2026 · similarity 0.78)
- QCircuitBench: A Large-Scale Dataset for Benchmarking Quantum Algorithm Design (NeurIPS 2025 · similarity 0.77)
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.
