AI Paper Atlas

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

Backpropagated Gradient Representations for Anomaly Detection

Gukyeong Kwon, Mohit Prabhushankar, Dogancan Temel, Ghassan AlRegib

ECCV 2020 · Label-efficient and robust learning › OOD and anomaly detection · approach: Deep one-class and tabular anomaly detection · 79 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 gradient constraint and score with gradient loss (ablation)CAE · CIFAR-10 (one-class, avg AUROC)AUROC: 0.564 -> 0.661Improved
add gradient constraint (reconstruction score) (ablation)CAE · CIFAR-10 (one-class, avg AUROC)AUROC: 0.564 -> 0.554No clear effect
add gradient constraint and score with gradient loss (ablation)VAE · CIFAR-10 (one-class, avg AUROC)AUROC: 0.583 -> 0.647Improved
add gradient constraint (latent loss score) (ablation)VAE · CIFAR-10 (one-class, avg AUROC)AUROC: 0.583 -> 0.550Hurt
add latent (KL) constraint to CAE, reconstruction score (ablation)CAE · CIFAR-10 (one-class, avg AUROC)AUROC: 0.564 -> 0.526Hurt
use all decoder layers' gradients instead of first layer (ablation)GradCon · CURE-TSR ExposureAUROC: 0.859 -> 0.891Improved
use all decoder layers' gradients instead of 4th layer only (ablation)GradCon · CIFAR-10 (gradient loss per decoder layer)AUROC: 0.605 -> 0.661Improved
combine reconstruction error with gradient loss as score (GradCon vs Grad only) (ablation)GradCon · fMNIST (10% outliers)AUC: 0.931 -> 0.938Improved
combine reconstruction error with gradient loss as score (GradCon vs Grad only) (ablation)GradCon · fMNIST (50% outliers)F1: 0.870 -> 0.871No clear effect
increase gradient-loss weight beta up to 2 alpha (ablation)GradCon · CIFAR-10 (one-class, avg AUROC)AUROCImproved
replace adversarial/autoregressive models with CAE plus gradient lossGradCon · CIFAR-10 (one-class, avg AUROC)AUROC: 0.657 -> 0.664Improved
replace adversarial/autoregressive models with CAE plus gradient lossGradCon · MNIST (one-class, avg AUROC)AUROC: 0.975 -> 0.973No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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