AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Effective End-to-end Unsupervised Outlier Detection via Inlier Priority of Discriminative Network

Siqi Wang, Yijie Zeng, Xinwang Liu, En Zhu, Jianping Yin, Chuanfu Xu, Marius Kloft

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 74 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
use end-to-end negative-entropy score instead of feeding SSD representations to isolation forest (ablation)E3Outlier · CIFAR10 10%AUROC: 64.0 -> 83.5Improved
use end-to-end score instead of decoupled isolation forest (ablation)E3Outlier · MNIST 10%AUROC: 93.8 -> 94.1No clear effect
replace CAE with surrogate-supervision discriminative network (both with isolation forest) (ablation)SSD-IF · CIFAR10 10%AUROC: 54.1 -> 64.0Improved
replace CAE-based UOD with E3OutlierE3Outlier · CIFAR10 10%AUROC: 55.9 -> 83.5Improved
train CAE on the same K-times augmented data (ablation)CAE · MNIST 10%AUROC: 68.0 -> 55.5Hurt
tune CAE latent dimension to 64 (ablation)CAE · CIFAR10/CIFAR100 10%AUROC: 56.3/56.1No clear effect
add irregular affine and patch re-arranging operations to regular affine set (ablation)E3Outlier · five benchmarks 10%AUROCImproved
use negative entropy score instead of PL/MP (ablation)E3Outlier · five benchmarks 10%AUROC: up to 2.3% AUCImproved
use maximum-probability score instead of pseudo-label score (ablation)E3Outlier · five benchmarks 10%AUROCImproved
use ResNet-50/DenseNet-40 instead of WRN-10-4 (ablation)E3Outlier · CIFAR10/SVHN/CIFAR100AUROCMixed
train longer than 3 epochs (ablation)E3Outlier · five benchmarks 10%AUROCNo clear effect
increase outlier ratio (ablation)E3Outlier · five benchmarksAUROCHurt

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