Methods › Computer Vision › Feature Pyramid Blocks › PAFPN

PAFPN

124 papers tagged archive 2025-07-28

Introduced by Shu Liu et al. in Path Aggregation Network for Instance Segmentation

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

PAFPN is a feature pyramid module used in Path Aggregation networks (PANet) that combines FPNs with bottom-up path augmentation, which shortens the information path between lower layers and topmost feature.

PaperSourceSee Code · ShuLiu1993/PANet

Papers archive 2025-07-28

30 shown of 124, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 148 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object Detection69
object-detection63
Object33
Segmentation13
Real-Time Object Detection12
Semantic Segmentation12
GPU8
Autonomous Driving7
Data Augmentation7
Deep Learning7
Instance Segmentation7
2D Object Detection5
Image Classification5
Transfer Learning5
Small Object Detection4
Traffic Sign Detection4
image-classification4
Domain Adaptation3
Object Tracking3
Position3

Usage over time archive 2025-07-28

Papers per year tagged with PAFPN: 2016 to 2025, peak 33 33 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 1 paper 2018 2019: 4 papers 2019 2020: 17 papers 2020 2021: 28 papers 2021 2022: 33 papers 2022 2023: 21 papers 2023 2024: 10 papers 2024 2025: 9 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (124 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Feature Pyramid BlocksFeature Extractors

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections