AI Paper Atlas

Research map / Label-efficient and robust learning / Noisy labels

Correlated Uncertainty for Learning Dense Correspondences from Noisy Labels

Natalia Neverova, David Novotny, Andrea Vedaldi

NeurIPS 2019 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 20 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
train with uncertainty (full model) instead of MSE regression lossHG 1 stack DensePose · DensePose-COCO 5cm% points within threshold: 49.92 -> 52.40Improved
uncertainty training on top of 8-stack hourglassHG 8 stacks · DensePose-COCO 5cm% points within threshold: 56.04 -> 56.48Improved
uncertainty training on 2-stack hourglass at 20cmHG 2 stacks · DensePose-COCO 20cm% points within threshold: 85.99 -> 85.58No clear effect
add elementary uncertainty (simple) versus MSE (ablation)HG 1 stack · DensePose-COCO UV only (GT parsing) 1cm% points within threshold: 5.57 -> 6.71Improved
richer uncertainty models (iid, full) instead of simple/simple-2D (ablation)HG 1 stack · DensePose-COCO UV accuracy% points within threshold: 52.67 (simple-2D) -> 52.40 (full) at 5cmNo clear effect
richer correlated uncertainty (full) instead of simple (ablation)uncertainty model · DensePose-COCO human annotationsnegative log-likelihood: 1.3159 -> 2.14057Improved
feed ground truth labels to uncertainty head during training (ablation)full model · DensePose-COCO UV only (GT parsing)% points within threshold: 6.78 -> 7.18 (1cm); overall 10cm 74.69 -> 74.28Improved
fuse ensemble using predicted uncertainty instead of averaging (ablation)ensemble of simple models · DensePose-COCO 5cm% points within threshold: 54.26 -> 54.46Improved

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