AI Paper Atlas

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

Embedding Contrastive Unsupervised Features to Cluster in- and Out-of-Distribution Noise in Corrupted Image Datasets

Paul Albert, Eric Arazo, Noel E. O’Connor, Kevin McGuinness

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Robust fine-tuning for OOD generalization · 8 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 mixup (ablation)SNCF · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 61.66 -> 67.62Improved
add spectral embedding of unsupervised features before clustering (ID corr and rm OOD, no contrastive) (ablation)SNCF · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 54.81 -> 61.83Improved
add guided contrastive objective on top of mixup without noise correction (ablation)cross-entropy with mixup · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 59.54 -> 62.83Improved
use OOD samples in guided contrastive loss instead of removing them (ablation)SNCF with embedding · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 64.51 -> 65.22Improved
add equal sampling of clean, ID noisy and OOD samples per mini-batch (ablation)SNCF · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 65.22 -> 67.62Improved
add guided contrastive loss with embedding and ID correction (ablation)SNCF · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 61.40 -> 63.91Improved
use ID correction only without embedding or contrastive loss (ablation)cross-entropy · CIFAR-100 + ImageNet32 OOD (r_out 0.4, r_in 0.2)best accuracy: 58.94 -> 57.02Hurt
raise xi in OPTICS above 0.03 (ablation)SNCF clustering · CIFAR-100 + ImageNet32clustering accuracyHurt
replace Places365 with ImageNet32 as OOD corruptionSNCF · CIFAR-100 (r_out 0.4, r_in 0.4)best accuracy: 54.04 vs 50.95Mixed
use SNCF instead of RRL at high noiseRRL · CIFAR-100 + ImageNet32 OOD (r_out 0.6, r_in 0.2)best accuracy: 26.76 -> 53.26Improved
use SNCF instead of RRL on Places365 at low noiseRRL · CIFAR-100 + Places365 OOD (r_out 0.2, r_in 0.2)best accuracy: 72.62 -> 71.25Hurt
use SNCF instead of PropMix on CNWLPropMix · CNWL miniImageNet 32x32 (noise 40%)best accuracy: 56.22 -> 59.94Improved

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