Methods › Computer Vision › Feature Extractors

Feature Extractors

25 methods 1,067 papers tagged archive 2025-07-28

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 25 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.

FPN Feature Pyramid Network – 583
TS Spatio-temporal stability analysis – 242
PAFPN – 124
Bottom-up Path Augmentation – 123
DLA Deep Layer Aggregation – 94
TUM Thinned U-shape Module – 57
BiFPN – 48
NEAT Neural Attention Fields – 25
NAS-FPN – 11
Context Enhancement Module – 8
RFB Receptive Field Block – 8
FSAF – 7
SFAM Scale-wise Feature Aggregation Module – 5
Spatial Attention Module (ThunderNet) – 4
TridentNet Block – 4
MatrixNet – 3
Panoptic FPN – 3
Cross-resolution features – 2
FFMv1 Feature Fusion Module v1 – 2
FFMv2 Feature Fusion Module v2 – 2
Low-level backbone – 2
MLFPN – 2
Streaming Module – 2
Feature Intertwiner – 1
High-level backbone – 1