AI Paper Atlas

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

Reliable Few-Shot Learning Under Dual Noises

Ji Zhang, Jingkuan Song, Lianli Gao, Nicu Sebe, Heng Tao Shen

TPAMI 2025 · Label-efficient and robust learning › Noisy labels · approach: Contrastive learning on noisy data · 42 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 DETA++ to six task-adaptation baselinesTSA, eTT, full-FT (MoCo, CLIP, DeiT, SwinT) · vanilla Meta-Dataset (ID-denoising)avg accuracy: +2.1 to +5.2Improved
add DETA++ to six baselines under OOD noisesix baselines · OOD-polluted Meta-Datasetavg accuracy: +2.7 to +6.6Improved
add DETA++ instead of DETAfull-FT SwinT · vanilla Meta-Datasetavg accuracy: 85.4 -> 86.5Improved
add DETA++ to TSA in standard protocolTSA (ImageNet-only) · Meta-Dataset standardavg accuracy: 70.7 -> 73.6Improved
add CoRA and clean prototype loss (ablation)baselines with NCC · Meta-Dataset 30% OODavg accuracy: 78.0 -> 79.8 (ID), 67.6 -> 69.2 (OOD)Improved
add LocalNCC (ablation)baselines with NCC · Meta-Dataset 30% OODavg accuracy: 79.8 -> 80.4 (ID), 69.2 -> 70.2 (OOD)Improved
add noise entropy maximization loss (ablation)baselines with NCC · Meta-Dataset 30% OODavg accuracy: 80.4 -> 81.2 (ID), 70.2 -> 71.6 (OOD)Improved
add IntraSwap (ablation)DETA++ · Meta-Dataset 30% OODavg accuracy: 81.2 -> 81.7 (ID), 71.6 -> 72.1 (OOD)Improved
vary noise-loss coefficient beta from 0.01 to 0.3 (ablation)DETA++ on full-FT MoCo · Meta-Dataset 30% OODavg accuracy: 75.5 -> 77.8 (ID), 63.5 -> 68.0 (OOD)Improved
increase beta from 0.3 to 1.0 (ablation)DETA++ on full-FT MoCo · Meta-Dataset 30% OODavg accuracy: 77.8 -> 75.8 (ID)Hurt
set region-filter threshold to 0.3 instead of 1.0 (ablation)DETA++ on full-FT MoCo · Meta-Dataset 30% OODavg accuracy: 75.4 -> 77.8 (ID), 65.5 -> 68.0 (OOD)Improved
use region size 112 instead of 48 (224x224 images) (ablation)DETA++ on full-FT MoCo · Meta-Dataset 30% OODavg accuracy: 74.0 -> 77.8 (ID), 63.2 -> 68.0 (OOD)Improved

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