Deep Nearest Neighbor Anomaly Detection

24 Feb 2020  ·  Liron Bergman, Niv Cohen, Yedid Hoshen ·

Nearest neighbors is a successful and long-standing technique for anomaly detection. Significant progress has been recently achieved by self-supervised deep methods (e.g. RotNet). Self-supervised features however typically under-perform Imagenet pre-trained features. In this work, we investigate whether the recent progress can indeed outperform nearest-neighbor methods operating on an Imagenet pretrained feature space. The simple nearest-neighbor based-approach is experimentally shown to outperform self-supervised methods in: accuracy, few shot generalization, training time and noise robustness while making fewer assumptions on image distributions.

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection Anomaly Detection on Anomaly Detection on Unlabeled ImageNet-30 vs Flowers-102 DN2 CLIP ViT ROC-AUC 93.2 # 3
Network ViT # 1
Anomaly Detection Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200 DN2 CLIP ViT ROC-AUC 93.8 # 2
Network ViT # 1
Anomaly Detection One-class CIFAR-10 DN2 AUROC 92.5 # 14

Methods


No methods listed for this paper. Add relevant methods here