</> Code with Papers by Syntology

Methods › Computer Vision › Feature Extractors › FPN

Feature Pyramid Network

FPN

583 papers tagged archive 2025-07-28

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

A Feature Pyramid Network, or FPN, is a feature extractor that takes a single-scale image of an arbitrary size as input, and outputs proportionally sized feature maps at multiple levels, in a fully convolutional fashion. This process is independent of the backbone convolutional architectures. It therefore acts as a generic solution for building feature pyramids inside deep convolutional networks to be used in tasks like object detection.

The construction of the pyramid involves a bottom-up pathway and a top-down pathway.

The bottom-up pathway is the feedforward computation of the backbone ConvNet, which computes a feature hierarchy consisting of feature maps at several scales with a scaling step of 2. For the feature pyramid, one pyramid level is defined for each stage. The output of the last layer of each stage is used as a reference set of feature maps. For ResNets we use the feature activations output by each stage’s last residual block.

The top-down pathway hallucinates higher resolution features by upsampling spatially coarser, but semantically stronger, feature maps from higher pyramid levels. These features are then enhanced with features from the bottom-up pathway via lateral connections. Each lateral connection merges feature maps of the same spatial size from the bottom-up pathway and the top-down pathway. The bottom-up feature map is of lower-level semantics, but its activations are more accurately localized as it was subsampled fewer times.

Source: Feature Pyramid Networks for Object DetectionSee Code · facebookresearch/Detectron

Papers archive 2025-07-28

30 shown of 583, 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 351 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 Detection342
object-detection311
Object192
Semantic Segmentation96
Instance Segmentation62
Segmentation60
Image Classification43
image-classification27
Data Augmentation25
GPU25
Classification23
Decoder23
Knowledge Distillation23
Autonomous Driving22
General Classification22
Real-Time Object Detection21
Text Classification19
Deep Learning18
Pedestrian Detection18
text-classification18

Usage over time archive 2025-07-28

Papers per year tagged with FPN: 2016 to 2025, peak 109 109 0 2016: 1 paper 2016 2017: 5 papers 2017 2018: 20 papers 2018 2019: 82 papers 2019 2020: 102 papers 2020 2021: 109 papers 2021 2022: 99 papers 2022 2023: 80 papers 2023 2024: 64 papers 2024 2025: 21 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (583 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 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