AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Part-aware Prototype Network for Few-shot Semantic Segmentation

Yongfei Liu, Xiangyi Zhang, Songyang Zhang, Xuming He

ECCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 404 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
decompose holistic prototype into part-aware prototypes (without global context) (ablation)PANet* baseline · COCO-20i split-A 1-way 1-shotmean-IoU: 22.95 -> 23.35Improved
add global context to part-aware prototypes (ablation)PAP · COCO-20i split-A 1-way 1-shotmean-IoU: 23.35 -> 25.02Improved
add semantic branch auxiliary loss (ablation)PAP · COCO-20i split-A 1-way 1-shotmean-IoU: 25.02 -> 25.71Improved
add unlabeled data with graph attention refinement (step-2 GNN) (ablation)PAP + SEM · COCO-20i split-A 1-way 1-shotmean-IoU: 26.34 -> 27.16Improved
add unlabeled data without step-2 GNN (ablation)PAP + SEM · COCO-20i split-A 1-way 1-shotmean-IoU: 25.71 -> 26.34Improved
add unlabeled support data (ablation)PPNet ResNet-50 · PASCAL-5i 1-way 1-shotmean-IoU: 51.50 -> 52.84Improved
add unlabeled support data (ablation)PPNet ResNet-50 · PASCAL-5i 1-way 5-shotmean-IoU: 61.96 -> 62.97Improved
add unlabeled support data (ablation)PPNet ResNet-50 · PASCAL-5i 2-way 1-shotmean-IoU: 50.24 -> 51.65Improved
add unlabeled support data (ablation)PPNet ResNet-50 · COCO-20i split-A 1-way 5-shotmean-IoU: 36.24 -> 36.73Improved
replace holistic prototype (PANet*) with PPNet w/o unlabeled dataPANet* ResNet-50 · PASCAL-5i 1-way 5-shotmean-IoU: 59.26 -> 61.96Improved
replace PPNet with ResNet-101 backbone instead of ResNet-50PPNet · PASCAL-5i 1-way 5-shotmean-IoU: 62.97 -> 65.10Improved
PPNet versus multi-scale PGNet in the 1-shot settingPPNet ResNet-50 · PASCAL-5i 1-way 1-shotmean-IoU: 52.84 vs 56.00Hurt

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