AI Paper Atlas

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

Contextualizing Meta-Learning via Learning to Decompose

Han-Jia Ye, Da-Wei Zhou, Lanqing Hong, Zhenguo Li, Xiu-Shen Wei, De‐Chuan Zhan

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-augmentation and meta-objectives · 11 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 LeadNet latent-attribute decomposition instead of ProtoNet-style single embeddingProtoNet · Colored-Kuzushiji DrawClass std=0.001 1-shot 5-wayaccuracy: 77.13 -> 84.43Improved
add LeadNet instead of MetaOptNet on cross-domain MiniImageNet to CUBMetaOptNet · MiniImageNet to CUB cross-domain 5-shot 5-wayaccuracy: 64.98 -> 67.89Improved
add LeadNet instead of MetaOptNet on cross-domain 1-shotMetaOptNet · MiniImageNet to CUB cross-domain 1-shot 5-wayaccuracy: 44.79 -> 44.82No clear effect
add latent attribute decomposition versus plain supervised 16-way classifier on digit attribute (ablation)SL · Colored MNIST digit attributeaccuracy: 49.25 -> 70.89Improved
add LeadNet instead of CSL on digit attributeCSL · Colored MNIST digit attributeaccuracy: 61.60 -> 70.89Improved
use LeadNet without attribute labels instead of PAN-Supervised with attribute labelsPAN-Supervised · UT-Zappos50K 5-shot 5-wayaccuracy: 46.92 -> 48.29Improved
add attribute supervision to ProtoNet (ProtoAttribute)ProtoNet · UT-Zappos50K 1-shot 5-wayaccuracy: 38.19 -> 38.75Mixed
add LeadNet instead of FEAT on MiniImageNetFEAT · MiniImageNet 1-shot 5-wayaccuracy: 66.78 -> 67.32Improved
add LeadNet instead of CGCS-Trans on CUBCGCS-Trans · CUB 1-shot 5-wayaccuracy: 76.69 -> 79.05Improved
add LeadNet instead of wave-SAN with ResNet-10 cross-domain 5-shotwave-SAN · MiniImageNet to CUB cross-domain 5-shot 5-way (ResNet-10)accuracy: 71.16 -> 70.88Hurt
add LeadNet instead of HSML on regressionHSML · Random-component regression 10-shotMSE: 0.161 -> 0.121Improved

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