Adaptive feature refinement with information preservation for multiclass unsupervised anomaly detection
Abstract Recent advancements in anomaly detection have shown significant potential across various industrial domains. However, a wide range of unpredictable defect types emerge in the real world, and anomaly images are often challenging to obtain, making traditional methods less suitable. To address...
Shranjeno v:
| Principais autores: | , , , , , , , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
Taylor & Francis Group
2026-06-01
|
| Serija: | Journal of Information Display |
| Teme: | |
| Online dostop: | https://doi.org/10.1007/s44469-026-00014-9 |
| Oznake: |
Brez oznak, prvi označite!
|