Research map / Label-efficient and robust learning / OOD and anomaly detection
Divide-and-Assemble: Learning Block-Wise Memory for Unsupervised Anomaly Detection
Jinlei Hou, Yingying Zhang, Qiaoyong Zhong, Di Xie, Shiliang Pu, Hong Zhou
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 pixel-wise memory module (MemAE) (ablation) | AE · MVTec AD | AUROC: 0.794 -> 0.802 | No clear effect |
| add plain skip connections (ablation) | AE · MVTec AD | AUROC: 0.794 -> 0.736 | Hurt |
| use multi-scale block-wise memory module (ablation) | AE · MVTec AD | AUROC: 0.794 -> 0.845 | Improved |
| add adversarially learned representation (ablation) | DAAD · MVTec AD | AUROC: 0.845 -> 0.895 | Improved |
| set division rate to 8 rather than 1 (ablation) | block-wise memory · MVTec AD | AUROC: 0.716 -> 0.845 | Improved |
| increase division rate from 8 to 16 (ablation) | block-wise memory · MVTec AD | AUROC: 0.845 -> 0.813 | Hurt |
| add adversarial loss alone (ablation) | DAAD · MVTec AD | AUROC: 0.845 -> 0.847 | No clear effect |
| add alignment loss (ablation) | DAAD · MVTec AD | AUROC: 0.847 -> 0.855 | Improved |
| add alignment score L(x) to anomaly score (ablation) | DAAD · MVTec AD | AUROC: 0.855 -> 0.874 | Improved |
| fuse reconstruction score R(x) with L(x) (ablation) | DAAD · MVTec AD | AUROC: 0.874 -> 0.895 | Improved |
| add adversarial representation components (ablation) | AE · MVTec AD | AUROC: 0.794 -> 0.835 | Improved |
| add adversarial representation components (ablation) | MemAE · MVTec AD | AUROC: 0.802 -> 0.853 | 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.
- OCGAN — OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations (CVPR 2019) · better on 1 of 1 shared result
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
- MaskAD: Parallel Masked Autoencoder for Multi-class Unsupervised Anomaly Detection (AAAI 2026 · similarity 0.90)
- DecAD: Decoupling Anomalies in Latent Space for Multi-Class Unsupervised Anomaly Detection (ICCV 2025 · similarity 0.88)
- Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning (AAAI 2025 · similarity 0.87)
- A Diffusion-Based Framework for Multi-Class Anomaly Detection (AAAI 2024 · similarity 0.87)
- Long-Tailed Anomaly Detection with Learnable Class Names (CVPR 2024 · similarity 0.87)
- Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection (CVPR 2025 · similarity 0.86)
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.
