AI Paper Atlas

Research map / Large language models / AI and society

Toward Few-Shot Learning in the Open World: A Review and Beyond

Hui Xue, Yuexuan An, Yongchun Qin, Wenqian Li, Yixin Wu, Yongjuan Che, Pengfei Fang, Min-Ling Zhang

TPAMI 2025 · Large language models › AI and society · approach: Social-science view of AI evaluation

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 metric-based weighting (PCL) instead of gradient-based Nested-MAMLnoisy few-shot learning · miniImageNet 5-shot, 40% noiseaccuracy: 56.46 -> 67.64Improved
raise symmetric support-set noise from 0% to 40%DETA · miniImageNet 5-shotaccuracy: 70.21 -> 57.04Hurt
raise symmetric support-set noise from 0% to 40%PCL · miniImageNet 5-shotaccuracy: 70.31 -> 67.64Hurt
raise symmetric support-set noise from 0% to 40%RNNP · miniImageNet 5-shotaccuracy: 68.38 -> 51.62Hurt
use test-time adaptation (DETA) instead of meta-training weighting (IDEAL)sample-selection NFSL · miniImageNet 5-shot, 40% noiseaccuracy: 56.45 -> 57.04Mixed
add class semantics to model the unknown class (ATT-G vs ATT)ATT · miniImageNet 1-shot open-setAUROC: 71.35 -> 72.41Improved
add global energy open scores (GEL)few-shot open-set recognition · miniImageNet 5-shotAUROC: 82.29 vs 81.04Improved
use the smoothed variant ProCAMsm instead of ProCAMProCAM · miniImageNet 1-shot open-setAUROC: 71.41 -> 71.09No clear effect
use CLIP language-image pretraining (CPE-CLIP)incremental few-shot learning · CIFAR-100 incrementalperformance drop (PD): 21.05 -> 7.31Improved
add unlabeled samples (UadCE) to data-based incremental learningdata-strategy IFSL · CUB-200 incrementalperformance drop (PD): 14.45 vs 22.04Improved
use attention fusion across base and novel classes (BiDist)network-ensemble IFSL · CIFAR-100 incrementalperformance drop (PD): 22.89 vs 34.73Improved

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