Methods › Computer Vision › Feature Pyramid Blocks

Feature Pyramid Blocks

10 methods 248 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 10 of the 10 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 6 of 10 methods:

Feature Pyramid Blocks are a basic component in recognition systems for detecting objects at different scales.

Text 2, carried by 4 of 10 methods:

Feature Extractors for object detection are modules used to construct features that can be used for detecting objects. They address issues such as the need to detect multiple-sized objects in an image (and the need to have representations that are suitable for the different scales).

Methods

All 10 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

PAFPN – 124
BiFPN – 48
Attention Pooling – 46
NAS-FPN – 11
RFP Recursive Feature Pyramid – 10
Balanced Feature Pyramid – 7
FPG Feature Pyramid Grid – 5
MLFPN – 2
ASFF Adaptively Spatial Feature Fusion – 1
Exact Fusion Model – 1