AI Paper Atlas

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

An accurate detection is not all you need to combat label noise in web-noisy datasets

Paul Albert, Kevin McGuinness, Eric Arazo, Tarun Krishna, Noel O Connor, Jack Valmadre

ECCV 2024 · Label-efficient and robust learning › Noisy labels · approach: Noisy cross-modal hashing and multi-label · 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
alternate noise detection between PLS and linear-separation metric every epoch (LSA) (ablation)PLS · CNWL 20% noiseaccuracy: 62.30 -> 64.20Improved
use OR combination of PLS and linear-separation detections (ablation)PLS-LSA · CNWL 20% noiseaccuracy: 62.30 -> 58.79Hurt
use accurate linear-separation noise detector alone instead of PLS (ablation)noise-robust training · CNWL 80% noiseaccuracy: 48.71 -> 47.11Hurt
use accurate linear-separation noise detector alone instead of PLS (ablation)noise-robust training · CNWL 20% noiseaccuracy: 62.30 -> 62.97Mixed
add strong data augmentation to PLS-LSA (ablation)PLS-LSA · CNWL 80% noisetop-1 accuracy: 43.55 -> 48.20Improved
add SimCLR initialization to PLS-LSA (ablation)PLS-LSA · mini-WebVisiontop-1 accuracy: 78.68 -> 81.36Improved
add SimCLR initialization to PLS-LSA (ablation)PLS-LSA · CNWL 20% noisetop-1 accuracy: 64.04 -> 64.61No clear effect
add co-training with two networks (PLS-LSA+)PLS-LSA · CNWL 80% noisetop-1 accuracy: 49.53 -> 52.03Improved
apply PLS-LSA on fine-grained web datasets with ImageNet initPLS · Web-Aircrafttop-1 accuracy: 87.58 -> 87.70No 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