AI Paper Atlas

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

Meta Navigator: Search for a Good Adaptation Policy for Few-Shot Learning

Chi Zhang, Henghui Ding, Guosheng Lin, Ruibo Li, Changhu Wang, Chunhua Shen

ICCV 2021 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-learning analysis and benchmarks · 50 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
search adaptation policies per stage instead of randomly sampling policies (ablation)random search · miniImageNet 5-way 5-shotaccuracy: 77.97 -> 82.66Improved
search adaptation policies per stage instead of randomly sampling policies (ablation)random search · miniImageNet 5-way 1-shotaccuracy: 64.10 -> 65.91Improved
search adaptation policies instead of random sampling (cross-domain) (ablation)random search · miniImageNet to CUB 10-shotaccuracy: 71.64 -> 81.05Improved
search policies instead of fixed Baseline++ policy (cross-domain) (ablation)Baseline++ · miniImageNet to CUB 10-shotaccuracy: 76.13 -> 81.05Improved
use searched policy instead of plain fine-tuningfinetune · miniImageNet 5-way 1-shotaccuracy: 44.81 -> 65.91Improved
use searched policy instead of MAML policyMAML · miniImageNet 5-way 5-shotaccuracy: 75.80 -> 82.66Improved
use searched policy instead of ProtoNets policyProtoNets · miniImageNet 5-way 10-shotaccuracy: 82.66 -> 85.46Improved
search policy instead of fixed Baseline++ on cross-domain 5-shotBaseline++ · miniImageNet to CUB 5-shotaccuracy: 70.01 -> 72.43Improved
add multi-crop testing (ablation)Meta Navigator · tieredImageNet 5-way 1-shotaccuracy: 73.52 -> 74.58Improved
add multi-crop testing (ablation)Meta Navigator · miniImageNet 5-way 1-shotaccuracy: 65.91 -> 67.14Improved
add multi-crop testing (ablation)Meta Navigator · FC100 5-way 5-shotaccuracy: 59.93 -> 61.33Improved
compare with DeepEMD on FC100 5-shotMeta Navigator · FC100 5-way 5-shotaccuracy: 63.22 vs 59.93Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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