AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Memorizing Normality to Detect Anomaly: Memory-Augmented Deep Autoencoder for Unsupervised Anomaly Detection

Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, Anton van den Hengel

ICCV 2019 · Label-efficient and robust learning › OOD and anomaly detection · approach: Deep one-class and tabular anomaly detection · 2,024 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add memory module to autoencoder (ablation)AE · MNISTaverage AUC: 0.9619 -> 0.9751Improved
add memory module to autoencoder (ablation)AE · CIFAR-10average AUC: 0.5706 -> 0.6088Improved
add sparse shrinkage and entropy loss to memory addressing (ablation)MemAE-nonSpar · MNISTaverage AUC: 0.9725 -> 0.9751Improved
add sparse shrinkage and entropy loss to memory addressing (ablation)MemAE-nonSpar · CIFAR-10average AUC: 0.6058 -> 0.6088Improved
add memory module to autoencoder (ablation)AE · UCSD-Ped2AUC: 0.917 -> 0.941Improved
add memory module to autoencoder (ablation)AE · CUHK AvenueAUC: 0.810 -> 0.833Improved
add memory module to autoencoder (ablation)AE · ShanghaiTechAUC: 0.697 -> 0.712Improved
add sparse addressing to memory (ablation)MemAE-nonSpar · ShanghaiTechAUC: 0.688 -> 0.712Improved
add memory module to autoencoder (ablation)AE · KDDCUP99F1: 0.9342 -> 0.9641Improved
add hard shrinkage to MemAE (ablation)MemAE w/o Shrinkage · UCSD-Ped2AUC: 0.9324 -> 0.9410Improved
add entropy loss to MemAE (ablation)MemAE w/o Entropy loss · UCSD-Ped2AUC: 0.9372 -> 0.9410Improved
add l1 sparsity regularization on latent features of AE (ablation)AE · UCSD-Ped2AUC: 0.9170 -> 0.9286Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy