AI Paper Atlas

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

Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty

Jeffrey Ryan Willette, Hae Beom Lee, Juho Lee, Sung Ju Hwang

ICLR 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 0 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 meta-learned diagonal or low-rank class covariances with scaled-energy inferencefew-shot classifiers · Omniglot OOD classes, 5-way 5-shotECE: 48.01±0.76 -> 33.19±0.94Improved
Use meta-learned diagonal or low-rank class covariances with scaled-energy inferencefew-shot classifiers · Omniglot OOD classes, 20-way 1-shotECE: 35.62±0.49 -> 49.28±1.21Hurt
Use meta-learned diagonal or low-rank class covariances with scaled-energy inferencefew-shot classifiers · MiniImageNet OOD classes, 5-way 1-shotECE: 29.86±0.73 -> 17.19±1.80Improved
Use meta-learned diagonal covariance factorsfew-shot classifiers · Omniglot-C, 5-way 5-shotECE: 24.85±13.12 -> 5.87±2.58Improved
Use meta-learned diagonal covariance factorsfew-shot classifiers · MiniImageNet-C, 5-way 1-shotECE: 12.32±3.84 -> 8.13±3.72Improved
Use meta-learned diagonal covariance factorsfew-shot classifiers · Meta-moons OODECE: 45.74±4.19 -> 15.66±2.65Improved
Use meta-learned diagonal covariance factorsfew-shot classifiers · Meta-Gaussians OODECE: 62.60±6.57 -> 42.55±0.98Improved
Use rank-1 covariance factors instead of diagonal covariance (ablation)Ours · Omniglot-C, 5-way 5-shotECE: 5.87±2.58 -> 6.10±2.87Hurt
Use rank-2 covariance factors instead of diagonal covariance (ablation)Ours · Omniglot-C, 5-way 5-shotECE: 5.87±2.58 -> 6.62±3.09Hurt
Use rank-4 covariance factors instead of diagonal covariance (ablation)Ours · Omniglot-C, 5-way 5-shotECE: 5.87±2.58 -> 7.10±3.40Hurt
Use rank-8 covariance factors instead of diagonal covariance (ablation)Ours · Omniglot-C, 5-way 5-shotECE: 5.87±2.58 -> 7.05±3.42Hurt
Use rank-1 covariance factors instead of diagonal covariance (ablation)Ours · MiniImageNet-C, 5-way 1-shotECE: 8.13±3.72 -> 9.02±3.83Hurt

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