Deep Nearest Neighbor Anomaly Detection
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 AbstractTasks
Datasets
CIFAR-10
Oxford 102 Flower
Results from the Paper
Ranked #2 on
Anomaly Detection
on Anomaly Detection on Unlabeled ImageNet-30 vs CUB-200
(using extra training data)
