AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

Huaxi Huang, Junjie Zhang, Jian Zhang, Qiang Wu, Chang Xu

AAAI 2021 · Label-efficient and robust learning › Semi-supervised learning · approach: Holistic semi-supervised pipelines · 24 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
replace Label Propagation with PoissonMBO (ablation)graph-based few-shot inference · miniImageNet 5-way 1-shotaccuracy: 74.04$\pm$1.00 -> 79.67$\pm$1.02Improved
add query feature calibration before PoissonMBO inference (ablation)PoissonMBO few-shot classifier · miniImageNet 5-way 1-shotaccuracy: 79.67$\pm$1.02 -> 80.00$\pm$0.83Improved
add unsupervised embedding transfer to Label Propagation (ablation)Label Propagation · miniImageNet 5-way 1-shotaccuracy: 74.04$\pm$1.00 -> 75.65$\pm$1.06Improved
add unsupervised embedding transfer to Label Propagation (ablation)Label Propagation · miniImageNet 5-way 5-shotaccuracy: 82.60$\pm$0.68 -> 84.46$\pm$0.68Improved
add unsupervised embedding transfer to PoissonMBO (ablation)PoissonMBO · miniImageNet 5-way 1-shotaccuracy: 79.67$\pm$1.02 -> 80.73$\pm$1.11Improved
add unsupervised embedding transfer to PoissonMBO (ablation)PoissonMBO · miniImageNet 5-way 5-shotaccuracy: 86.30$\pm$0.65 -> 87.41$\pm$0.63Improved
increase extra unlabeled samples from 0 to 200 (ablation)PTN · miniImageNet 5-way 1-shotaccuracy: 77.01$\pm$0.94 -> 82.66$\pm$0.97Improved
increase extra unlabeled samples from 0 to 200 (ablation)PTN · miniImageNet 5-way 5-shotaccuracy: 85.32$\pm$0.68 -> 88.43$\pm$0.76Improved
use unlabeled query samples for embedding transfer when Num_U is 0 (ablation)PTN versus PTN* · miniImageNet 5-way 1-shotaccuracy: 76.20$\pm$0.82 -> 77.01$\pm$0.94Improved
add distractor classes among unlabeled samples (ablation)PTN · miniImageNet 5-way 1-shotaccuracy: 82.66$\pm$0.97 -> 81.92$\pm$1.02Hurt
add distractor classes among unlabeled samples (ablation)PTN · tieredImageNet 5-way 5-shotaccuracy: 89.14$\pm$0.71 -> 88.06$\pm$0.62Hurt

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