AI Paper Atlas

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

Out-of-Distribution Detection with An Adaptive Likelihood Ratio on Informative Hierarchical VAE

Yewen Li, Chaojie Wang, Xiaobo Xia, Tongliang Liu, Xin Miao, Bo An

NeurIPS 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Spurious-aware OOD detection · 1 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 LLR>2 instead of LLR>1 as score (ablation)3-layer informative HVAE · CIFAR10/SVHNAUROC: 68.4 -> 93.0Improved
Use LLR>2 instead of LLR>1 as score (ablation)3-layer informative HVAE · FashionMNIST/MNISTAUROC: 97.5 -> 97.4No clear effect
Use LLR>k score instead of plain likelihood L (ablation)3-layer informative HVAE · CIFAR10/SVHNAUROC: 49.9 -> 93.0Improved
Use LLR>k score instead of plain likelihood L (ablation)3-layer informative HVAE · FashionMNIST/MNISTAUROC: 55.3 -> 97.4Improved
Use adaptive LLRada instead of fixed-k LLR>1 (ablation)3-layer informative HVAE · CIFAR10/SVHNAUROC: 68.4 -> 92.6Improved
Use adaptive LLRada instead of best fixed k (LLR>2) (ablation)3-layer informative HVAE · CIFAR10/SVHNAUROC: 93.0 -> 92.6No clear effect
Use informative hierarchical VAE instead of HVAEHVAE with LLRada · FashionMNIST, KMNIST OODAUROC: 86.4 -> 95.0Improved
Use informative hierarchical VAE instead of BIVABIVA with LLRada · FashionMNIST, notMNIST OODAUROC: 96.4 -> 99.7Improved
Use informative hierarchical VAE instead of HVAEHVAE with LLRada · CIFAR10, CelebA OODAUROC: 39.8 -> 72.1Improved
Use informative hierarchical VAE instead of HVAEHVAE with LLRada · CIFAR10, LFWPeople OODAUROC: 42.5 -> 83.0Improved
Use informative hierarchical VAE instead of BIVABIVA with LLRada · CIFAR10, Flower102 OODAUROC: 61.9 -> 63.4No clear effect
Use informative hierarchical VAE instead of HVAE on already-saturated OOD setsHVAE with LLRada · FashionMNIST, SmallNORB OODAUROC: 100 -> 100No clear effect

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