AI Paper Atlas

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

Full-Spectrum Out-of-Distribution Detection

Jingkang Yang, Kaiyang Zhou, Ziwei Liu

IJCV 2023 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 72 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 low-layer feature-statistics term p(x_n) to p(x) (SEM vs p(x) only) (ablation)SEM · FS-OOD DIGITS far-OODAUROC: 60.80 -> 69.73Improved
add low-layer feature-statistics term p(x_n) to p(x) (SEM vs p(x) only) (ablation)SEM · FS-OOD DIGITS near-OODAUROC: 87.28 -> 88.47Improved
use low-layer feature statistics instead of low-layer flattened features for p(x_n) (ablation)SEM · FS-OOD DIGITS near-OODAUROC: 86.54 -> 88.47Improved
use low-layer feature statistics instead of low-layer flattened features for p(x_n) (ablation)SEM · FS-OOD DIGITS far-OODAUROC: 61.26 -> 69.73Improved
add fine-tuning with L_cls before fitting the GMM (ablation)SEM · FS-OOD DIGITS near-OODAUROC: 83.03 -> 86.55Improved
add L_src(x) (compact ID statistics) to fine-tuning (ablation)SEM · FS-OOD DIGITS far-OODAUROC: 64.61 -> 68.40Improved
add negative augmented data L_src(x') to fine-tuning with L_src(x) (ablation)SEM · FS-OOD DIGITS near-OODAUROC: 87.42 -> 88.47Improved
add L_src(x) to fine-tuning that already has negative augmentation (ablation)SEM · FS-OOD DIGITS far-OODAUROC: 67.92 -> 69.73Improved
use M=3 GMM components for p(x_n) and M=10 for p(x) instead of M=1/M=20 (ablation)SEM · FS-OOD DIGITS near-OODAUROC: 84.47 -> 88.47Improved
SEM vs best baseline on notMNIST near-OOD (feature-based semantic score)SEM · FS-OOD DIGITS notMNISTFPR95: 99.99 -> 10.93Improved
use SEM instead of EBO/MSP/ODIN under covariate-shifted IDSEM · FS-OOD COVID near-OODAUROC: 45.47 -> 97.24Improved
use SEM instead of output-based scores on far-OOD of OBJECTSSEM · FS-OOD OBJECTS far-OODFPR95: 76.98 -> 89.87Hurt

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