AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

LibFewShot: A Comprehensive Library for Few-Shot Learning

Wenbin Li, Ziyi Wang, Xuesong Yang, Chuanqi Dong, Pinzhuo Tian, Tiexin Qin, Jing Huo, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Embedding adaptation for few-shot classification · 101 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 l2 normalization to RFS-simple test classifier (1-shot) (ablation)RFS-simple · miniImageNet 5-way 1-shotaccuracy: 58.69 -> 61.61Improved
replace logistic regression test-tuning with l2-normalized 1-NN (5-shot) (ablation)RFS-simple · miniImageNet 5-way 5-shotaccuracy: 78.80 -> 78.85Improved
replace logistic regression test-tuning with l2-normalized 1-NN (1-shot) (ablation)RFS-simple · miniImageNet 5-way 1-shotaccuracy: 61.61 -> 60.64No clear effect
add episodic fine-tuning after pre-training with global labels (Two Stages) (ablation)ProtoNet · miniImageNet 5-way 1-shotaccuracy: 6.46% improvement to 63.56%Improved
add episodic fine-tuning after global pre-training (Two Stages) (ablation)DN4 · miniImageNet 5-way 1-shotaccuracy: 4.34% improvement to 63.02%Improved
add episodic fine-tuning after global pre-training (Two Stages) (ablation)R2D2 · miniImageNet 5-way 1-shotaccuracy: 2.52% improvement to 62.04%Improved
add cutmix strong augmentation (1-shot) (ablation)ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 1-shotaccuracy: +2.24%, +3.75%, +2.08%Improved
add cutmix strong augmentation (5-shot) (ablation)ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 5-shotaccuracy: +3.69%, +5.71%, +2.2%Improved
add mixup augmentation (5-shot) (ablation)ProtoNet, R2D2, RFS-simple · miniImageNet 5-way 5-shotaccuracy: +2.57%, +2.54%, +0.41%Improved
add self-distillation knowledge distillation (5-shot) (ablation)ProtoNet, DN4, R2D2 · miniImageNet 5-way 5-shotaccuracy: +1.86%, +1.73%, +1.94%Improved
add self-distillation knowledge distillation (1-shot) (ablation)ProtoNet, DN4, R2D2 · miniImageNet 5-way 1-shotaccuracy: +2.18%, +0.65%, +2.06%Improved
add rotation-prediction self-supervision (1-shot) (ablation)ProtoNet, DN4, R2D2 · miniImageNet 5-way 1-shotaccuracy: +0.94%, +0.55%, +2.57%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