Research map / Label-efficient and robust learning / OOD and anomaly detection
Multi-Prototype Compactness and Boundary-Aware Synthesis for Unsupervised Anomaly Detection
Kailun Liao, Jianfeng Yang, Tao Tao, Wenfei Wu, Jiaming Jiang, Jinsheng Xiao
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 |
|---|---|---|---|
| add multi-prototype compact constraint (MPCC) to single-prototype baseline (ablation) | PGBL baseline · MVTec-AD | I-AUROC: 96.3 -> 97.0 | Improved |
| add DBR discriminator trained on Gaussian-noise pseudo-anomalies (ablation) | MPCC model · MVTec-AD | I-AUROC: 97.0 -> 99.2 | Improved |
| replace Gaussian-noise anomaly synthesis with boundary-aware synthesis (BAAS) (ablation) | PGBL · MVTec-AD | I-AUROC: 99.2 -> 99.8 | Improved |
| replace Gaussian-noise anomaly synthesis with BAAS (ablation) | PGBL · MVTec-AD | P-AUPRO: 94.3 -> 95.0 | Improved |
| vary number of cluster prototypes M from 1 to 30 (ablation) | PGBL · MVTec-AD and VisA | I-AUROC: peak at M = 10: 99.8 (MVTec-AD), 98.0 (VisA) | Mixed |
| vary k-NN neighborhood size k in BAAS (ablation) | PGBL · MVTec-AD | I-AUROC | No clear effect |
| increase noise variance sigma^2 to very large values (ablation) | BAAS · MVTec-AD | I-AUROC | Hurt |
| change pretrained backbone (ResNet50, ResNet101, WideResNet50, ViT-B/16, ViT-L/16) (ablation) | PGBL · MVTec-AD | I-AUROC / P-AUROC: WideResNet50 P-AUROC 98.6 | No clear effect |
| change random seed for prototype initialization (ablation) | PGBL · MVTec-AD | I-AUROC: 99.8 / 99.8 / 99.7 / 99.8 | No clear effect |
| use PGBL instead of SimpleNet (adds BAAS k-NN) | inference/training cost · Real-IAD | training latency (ms): 7.83 -> 21.12 | Hurt |
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.
- SimpleNet — SimpleNet: A Simple Network for Image Anomaly Detection and Localization (CVPR 2023) · better on 2 of 3 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
- ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection (ECCV 2026 · similarity 0.88)
- Prototypical Residual Networks for Anomaly Detection and Localization (CVPR 2023 · similarity 0.88)
- AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios (CVPR 2025 · similarity 0.87)
- Towards Training-free Anomaly Detection with Vision and Language Foundation Models (CVPR 2025 · similarity 0.86)
- 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly Detection (AAAI 2025 · similarity 0.86)
- Exploring Intrinsic Normal Prototypes within a Single Image for Universal Anomaly Detection (CVPR 2025 · similarity 0.85)
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.
