Methods › Computer Vision › Feature Pyramid Blocks › NAS-FPN

NAS-FPN

11 papers tagged archive 2025-07-28

Introduced by Golnaz Ghiasi et al. in NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection

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

NAS-FPN is a Feature Pyramid Network that is discovered via Neural Architecture Search in a novel scalable search space covering all cross-scale connections. The discovered architecture consists of a combination of top-down and bottom-up connections to fuse features across scales

PaperSourceSee Code · tensorflow/tpu

Papers archive 2025-07-28

11 shown of 11, 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

17 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 Detection9
object-detection8
Object5
Neural Architecture Search4
Semantic Segmentation4
Data Augmentation3
Instance Segmentation3
Segmentation3
Image Augmentation2
Image Classification2
Real-Time Object Detection2
GPU1
General Classification1
Point Cloud Registration1
Real-Time Semantic Segmentation1
Robust Object Detection1
image-classification1

Usage over time archive 2025-07-28

Papers per year tagged with NAS-FPN: 2019 to 2024, peak 5 5 0 2019: 5 papers 2019 2020: 3 papers 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 0 papers 2023 2024: 1 paper 2024
Papers per year the archive tags with this method, by the paper's archive date (11 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