AI Paper Atlas

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

Prior Guided Feature Enrichment Network for Few-Shot Segmentation

Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, Jiaya Jia

TPAMI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot segmentation · 720 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 top-down inter-scale path to FEM (ablation)PFENet FEM · PASCAL-5i 1-shotmean class mIoU: 59.8 -> 60.8Improved
use bottom-up instead of top-down path (ablation)PFENet FEM · PASCAL-5i 5-shotmean class mIoU: 61.9 -> 60.7Hurt
add bidirectional TD+BU path instead of TD (ablation)PFENet FEM · PASCAL-5i 5-shotmean class mIoU: 61.9 -> 62.0No clear effect
replace FEM with PPM (ablation)Baseline · PASCAL-5i 1-shotmean class mIoU: 59.2 -> 57.1Hurt
add FEM with scales {60,30,15,8} to baseline (ablation)Baseline · PASCAL-5i 1-shotmean class mIoU: 56.3 -> 59.2Improved
add extra scale 4 to FEM (more parameters) (ablation)FEM · PASCAL-5i 1-shotmean class mIoU: 59.2 -> 58.9Hurt
add prior mask from fixed high-level features (ablation)Baseline + FEM · PASCAL-5i 1-shotmean class mIoU: 59.2 -> 60.8Improved
generate prior from learnable high-level features instead of fixed (ablation)VGG-16 baseline · PASCAL-5i 1-shotmean class mIoU: 53.3 -> 48.9Hurt
add prior from fixed high-level features (ablation)VGG-16 baseline · PASCAL-5i 1-shotmean class mIoU: 53.3 -> 55.4Improved
use average similarity instead of max for prior (ablation)Prior_FH · PASCAL-5i 1-shotmean class mIoU: 55.4 -> 55.1Hurt
use mask-pooled support feature for prior (ablation)Prior_FH · PASCAL-5i 1-shotmean class mIoU: 55.4 -> 54.7Hurt
add prior mask on totally unseen FSS-1000 classesBaseline · FSS-1000 unseen classesforeground IoU: 79.7 -> 80.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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