AI Paper Atlas

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

Robust Meta-Representation Learning via Global Label Inference and Classification

Ruohan Wang, Isak Falk, Massimiliano Pontil, Carlo Ciliberto

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-learning analysis and benchmarks · 7 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 rotation-augmented pre-training (4x classes) (ablation)MeLa pre-training · miniImageNet 1-shotaccuracy (%): 62.0 -> 64.5Improved
add rotation-augmented pre-training (4x classes) (ablation)MeLa pre-training · miniImageNet 5-shotaccuracy (%): 79.6 -> 81.5Improved
add rotation-augmented pre-training (4x classes) (ablation)MeLa pre-training · H-Aircraft 1-shotaccuracy (%): 79.2 -> 84.8Improved
add rotation-augmented pre-training (4x classes) (ablation)MeLa pre-training · tieredImageNet 1-shotaccuracy (%): 69.1 -> 69.5No clear effect
add rotation-augmented pre-training (4x classes) (ablation)MeLa pre-training · tiered-780 1-shotaccuracy (%): 78.0 -> 78.2No clear effect
use 640 classes with 60 samples per class instead of 64 classes (same dataset size) (ablation)standard pre-training · miniImageNet vs mini-60 1-shotaccuracy (%): 62.0 -> 63.9Improved
add local-constraint-aware clustering instead of K-means (ablation)MeLa pre-training · tieredImageNet 5-shotaccuracy (%): 78.8 -> 84.3Improved
add local-constraint-aware clustering instead of K-means (ablation)MeLa pre-training · miniImageNet 5-shotaccuracy (%): 76.9 -> 81.5Improved
use no-replacement task sampling instead of with-replacement (ablation)MeLa · miniImageNet 1-shotaccuracy (%): 65.8 -> 65.8No clear effect
raise pruning threshold q from 3 to 5 (ablation)MeLa pre-training · miniImageNet 5-shotaccuracy (%): 81.5 -> 80.9No clear effect
add meta fine-tuning with residual connections to pre-training (ablation)MeLa · miniImageNet 1-shotaccuracy (%): 64.5 -> 65.8Improved
add meta fine-tuning with residual connections to pre-training (ablation)MeLa · tieredImageNet 5-shotaccuracy (%): 84.3 -> 85.9Improved

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