AI Paper Atlas

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

Out-of-Distribution Detection with Boundary Aware Learning

Sen Pei, Xin Zhang, Bin Fan, Gaofeng Meng

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Provable and feature-based OOD detection · 5 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 BAL trivial-OOD discriminator loss L_t on top of softmax classifier (ablation)softmax baseline · CIFAR-10 vs TinyImageNet (DenseNet-BC)FPR95: 41.1 -> 17.9Improved
add shuffle loss L_s (ablation)BAL (L_t) · CIFAR-10 vs TinyImageNet (DenseNet-BC)FPR95: 17.9 -> 9.3Improved
add uniform loss L_u (ablation)BAL (L_t) · CIFAR-10 vs TinyImageNet (DenseNet-BC)FPR95: 17.9 -> 8.1Improved
add both shuffle and uniform loss (ablation)BAL (L_t) · CIFAR-10 vs TinyImageNet (DenseNet-BC)FPR95: 17.9 -> 5.0Improved
add both shuffle and uniform loss (ablation)BAL (L_t) · CIFAR-10 vs TinyImageNet (DenseNet-BC)AUPR_out: 96.0 -> 98.0Improved
use uniform sampling instead of Gaussian sampling of trivial OOD features (ablation)BAL · feature dim 2, CIFAR-10 vs TinyImageNetAUROC: 94.3 -> 96.5Improved
use uniform sampling instead of Gaussian sampling (ablation)BAL · feature dim 512AUROC: 98.1 -> 98.1No clear effect
use uniform sampling instead of Gaussian sampling (ablation)BAL · feature dim 1024AUROC: 98.5 -> 98.8Improved
raise lambda_c from 0.1 to 0.7 (ablation)BAL uniform loss · CIFAR-10 vs TinyImageNet (DenseNet-BC)AUROC: 94.8 -> 97.0Improved
raise lambda_c from 0.7 to 0.9 (ablation)BAL uniform loss · CIFAR-10 vs TinyImageNet (DenseNet-BC)AUROC: 97.0 -> 96.2Hurt
raise lambda_c from 0.1 to 0.9 (ablation)BAL uniform loss · CIFAR-10 vs TinyImageNet (DenseNet-BC)AUPR_out: 92.1 -> 97.1Improved
use BAL instead of ODINODIN · Fashion-MNIST ID, MNIST & Omniglot OODFPR95: 33.27 -> 9.20Improved

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