AI Paper Atlas

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

Prototype Completion for Few-Shot Learning

Baoquan Zhang, Xutao Li, Yunming Ye, Shanshan Feng

TPAMI 2023 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Alignment-based few-shot metric learning · 27 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 ProtoComNet prototype completion (ablation)mean-based prototypes · miniImagenet 5-way 1-shotaccuracy: 61.22 -> 65.62Improved
add ProtoComNet prototype completion (ablation)mean-based prototypes · miniImagenet 5-way 5-shotaccuracy: 78.72 -> 75.32Hurt
add PATNet to model unseen parts/attributes (ablation)ProtoComNet · miniImagenet 5-way 1-shotaccuracy: 65.62 -> 66.52Improved
add PATNet to model unseen parts/attributes (ablation)ProtoComNet · tieredImagenet 5-way 5-shotaccuracy: 80.78 -> 84.10Improved
add MeanFusion of mean and completed prototypes (ablation)ProtoComNet + PATNet · miniImagenet 5-way 5-shotaccuracy: 75.68 -> 81.65Improved
replace MeanFusion with two-step GaussFusion (ablation)ProtoComNet + PATNet · miniImagenet 5-way 1-shotaccuracy: 69.68 -> 76.05Improved
replace two-step estimation with improved EM in GaussFusion (ablation)GaussFusion · miniImagenet 5-way 1-shotaccuracy: 76.05 -> 79.01Improved
replace two-step estimation with improved EM in GaussFusion (ablation)GaussFusion · CUB-200-2011 5-way 1-shotaccuracy: 93.30 -> 93.78Improved
add GaussFusion under primitive-knowledge noise gamma=0.3 (ablation)prototype completion · miniImagenet 5-way 1-shotaccuracy: 42.53 -> 77.24Improved
add GaussFusion instead of MeanFusion under noise gamma=0.3 (ablation)prototype completion · tieredImagenet 5-way 1-shotaccuracy: 57.77 -> 81.51Improved
add ProtoComNet prototype completion (ablation)mean-based prototypes · CUB-200-2011 5-way 5-shotaccuracy: 91.36 -> 89.19Hurt
use EM-based estimation vs improved EM (ablation)GaussFusion · miniImagenet 5-way 1-shot (transductive)accuracy: 75.35 -> 79.01Improved

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