arXiv Computer Vision
What Memory Composition Does Not Tell Us About Anomaly Detection
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 25
What Remains Normal? Clean Images Miss Useful Near-Defect Normal Patches for Anomaly Detection
arXiv:2608.23299v1 Announce Type: new Abstract: Memory-based anomaly detectors store nominal training patches and score test patches against this memory. A patch selected for coverage therefore becom...
arXiv Computer Vision
Aug 25
When More References Hurt: Contamination-Aware DINOv2 Memory Banks for Few-Shot Steel Defect Detection
The paper investigates how to improve patch‑memory anomaly detectors for steel defect detection when additional industrial images may contain unseen defects. By filtering out the most suspicious 20% of patches from a contaminated reference bank and merging the remaining patches with a clean seed bank, the authors reduce contamination from 9.46% to 2.59% and achieve higher AUPRC scores compared to naive expansion or random removal. The method demonstrates that reference purity is a critical design factor and that unverified images can be beneficial only after explicit filtering.
Hugging Face Trending Papers
Jul 6
ProCon: Projection-Consistency Memory for Training-Free Anomaly Detection
Memory-based anomaly detection is attractive because it localizes defects from normal images without training a decoder or synthesizing pseudo anomalies. However, most memory methods still use the memory bank as a nearest-neighbor lookup table: a test patch is treated as normal if it has one nearby normal anchor.
arXiv Machine Learning
Aug 19
Training-Free Human-in-the-Loop Anomaly Detection via Memory Bank Correction
The paper introduces a training‑free, human‑in‑the‑loop anomaly detection framework that allows a domain expert to correct a PatchCore detector by editing its memory bank, without retraining or using gradients. Using only ten golden samples, operator corrections close a median 66% of the performance gap to a fully trained bank, improving 12 of 15 MVTec AD categories while harming none. The approach is evaluated with a rigorous held‑out protocol and shows that passive and active querying yield statistically indistinguishable gains, with a defect‑memory extension failing decisively.
arXiv AI
Aug 11
Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions
arXiv:2604. 06435v2 Announce Type: replace-cross Abstract: Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare.
arXiv Machine Learning
Aug 13
Patch-based Memory Gate Model in Time Series Foundation Model
arXiv:2509. 18751v4 Announce Type: replace Abstract: Recently reconstruction-based deep models have been widely used for time series anomaly detection, but as their capacity and generalization capability increase, these models tend to over-generalize, often reconstructing unseen anomalies accurately.