[KongchangAI]
Benchmark

Real-IAD

An anomaly detection benchmark dataset oriented toward real industrial scenarios. It is relatively large in scale and covers diverse defect types, and it supports evaluation under settings with different sample counts.

Timeline (last 90 days)

Oct 26

The paper covers 1-, 2-, and 4-shot benchmarks on MVTec-AD and VisA, and conducts a sample-count variation evaluation on Real-IAD, achieving state-of-the-art results compared with recent class-specific methods in all cases.

Unverified50%

All Facts (1)

Unverified

The paper covers 1-, 2-, and 4-shot benchmarks on MVTec-AD and VisA, and conducts a sample-count variation evaluation on Real-IAD, achieving state-of-the-art results compared with recent class-specific methods in all cases.

50%

Source Articles

Flownomaly: Few-Shot Anomaly Detection via Single-Step Conditional Mean RestorationOct 26