AI Paper Atlas

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

IRNet: Iterative Refinement Network for Noisy Partial Label Learning

Zheng Lian, Mingyu Xu, Lan Chen, Licai Sun, Bin Liu, Lei Feng, Jianhua Tao

TPAMI 2025 · Label-efficient and robust learning › Noisy labels · approach: Instance-dependent noise modeling · 12 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 IRNet to PiCOPiCO · CIFAR-10 (q=0.3, eta=0.3)accuracy: 82.25 -> 91.35Improved
add IRNet to CCCC · CIFAR-10 (q=0.1, eta=0.3)accuracy: 84.46 -> 89.92Improved
add IRNet to PiCOPiCO · CIFAR-10 (q=0.5, eta=0.3)accuracy: 68.75 -> 86.19Improved
add IRNet to PiCOPiCO · Kuzushiji-MNIST (last-epoch gap)best-last accuracy gap: 9.42%~12.46% -> 0.12%~0.14%Improved
add IRNet to PiCOPiCO · CIFAR-100 (q=0.01, eta=0.3)best accuracy: 58.97 -> 68.77Improved
add weak augmentation smoothness constraint (ablation)IRNet · CIFAR-10accuracy: 0.50%~1.90% improvement; 90.78 -> 92.38 at q=0.1Improved
add weak augmentation smoothness constraint (ablation)IRNet · CIFAR-100 (q=0.01)accuracy: 65.40 -> 68.77Improved
replace weak with strong augmentation (ablation)IRNet · CIFAR-10 (q=0.1)accuracy: 92.38 -> 91.43Hurt
use two strong augmentations instead of none (ablation)IRNet · CIFAR-100 (q=0.01)accuracy: 65.40 -> 61.70Hurt
increase weak augmentations from 1 to 2 (ablation)IRNet · CIFAR-10 (q=0.1)accuracy: 92.38 -> 92.68Mixed
add swapping (move lowest-confidence label out of candidates) (ablation)IRNet · CIFAR-10 (q=0.5)accuracy: 86.19 -> 84.15Hurt
add swapping (move lowest-confidence label out of candidates) (ablation)IRNet · CIFAR-100 (q=0.05)accuracy: 68.09 -> 67.19Hurt

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