AI Paper Atlas

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

Knockoffs-SPR: Clean Sample Selection in Learning With Noisy Labels

Yikai Wang, Yanwei Fu, Xinwei Sun

TPAMI 2023 · Label-efficient and robust learning › Noisy labels · approach: Noise-aware loss and pairwise methods · 18 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 most-confident label permutation instead of random permutation for the knockoff copy (ablation)Knockoffs-SPR · CIFAR-10 Sym. 40%accuracy (%): 92.0 -> 94.7Improved
use most-confident label permutation instead of random permutation (ablation)Knockoffs-SPR · CIFAR-10 Asy. 40%accuracy (%): 84.4 -> 93.5Improved
use most-confident label permutation instead of random permutation (ablation)Knockoffs-SPR · CIFAR-10 Sym. 80%FSR (%): 49.76 -> 26.72Improved
use most-confident label permutation instead of random permutation (ablation)Knockoffs-SPR · CIFAR-10 Sym. 80%accuracy (%): 84.6 -> 84.3No clear effect
add class-specific selection (ablation)Knockoffs-SPR · CIFAR-10 Sym. 80%accuracy (%): 83.0 -> 84.3Improved
add class-specific selection (ablation)Knockoffs-SPR · CIFAR-10 Sym. 40%accuracy (%): 94.4 -> 94.7Improved
add PCA preprocessing of features (ablation)Knockoffs-SPR · CIFAR-10 Sym. 80%accuracy (%): 10.0 -> 84.3Improved
add PCA preprocessing of features (ablation)Knockoffs-SPR · CIFAR-10 Sym. 40%accuracy (%): 81.7 -> 94.7Improved
add PCA preprocessing of features (ablation)Knockoffs-SPR · CIFAR-10 Asy. 40%accuracy (%): 93.7 -> 93.5No clear effect
use PCA instead of an extra linear layer for dimension reduction (ablation)Knockoffs-SPR · CIFAR-10 Sym. 80%accuracy (%): 79.3 -> 84.3Improved
use Knockoffs-SPR instead of SPRSPR · CIFAR-10 Sym. 80%accuracy (%): 78.0 -> 84.3Improved
use Knockoffs-SPR instead of SPRSPR · CIFAR-100 Sym. 80%accuracy (%): 38.1 -> 30.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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