AI Paper Atlas

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

Improving Few-Shot Learning through Multi-task Representation Learning Theory

Quentin Bouniot, Ievgen Redko, Romaric Audigier, Angélique Loesch, Amaury Habrard

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-learning analysis and benchmarks

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 spectral and norm regularization on linear predictorsMAML (C64) · miniImageNet 5-way 5-shotaccuracy: 64.47 -> 66.43Improved
add spectral and norm regularization on linear predictorsMAML (R12, pretrained) · miniImageNet 5-way 5-shotaccuracy: 81.24 -> 82.45Improved
add spectral and norm regularization on linear predictorsMAML (R12, pretrained) · tieredImageNet 5-way 5-shotaccuracy: 81.79 -> 81.28No clear effect
add spectral and norm regularization on linear predictorsMeta-Curvature (C64) · miniImageNet 5-way 5-shotaccuracy: 63.74 -> 65.67Improved
add spectral and norm regularization on linear predictorsMeta-Curvature (C64) · tieredImageNet 5-way 5-shotaccuracy: 71.95 -> 73.34Improved
add prototype normalizationProtoNet (C64) · miniImageNet 5-way 5-shotaccuracy: 65.1 -> 67.13Improved
add prototype normalizationProtoNet (R12) · miniImageNet 5-way 5-shotaccuracy: 77.92 -> 80.95Improved
add prototype normalizationProtoNet (R12) · tieredImageNet 5-way 1-shotaccuracy: 41.39 -> 68.44Improved
add prototype normalizationIMP (C64) · miniImageNet 5-way 1-shotaccuracy: 48.85 -> 50.69Improved
add prototype normalizationProtoNet (C64) · Omniglot 20-way 5-shotaccuracy: 98.80 -> 98.80No clear effect
add prototype normalizationIMP (C64) · Omniglot 20-way 1-shotaccuracy: 95.77 -> 95.85No clear effect
add spectral and norm regularization on linear predictorsMTL (R12) · miniImageNet 5-way 1-shotaccuracy: 55.73 -> 61.12Improved

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