Feature Extractors

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). Below you can find a continuously updating list of feature extractors for object detection.

METHOD YEAR PAPERS
FPN
2016 163
Bottom-up Path Augmentation
2018 12
PAFPN
2018 11
RFB
2017 5
Context Enhancement Module
2019 4
TUM
2018 4
BiFPN
2019 4
SFAM
2018 3
NAS-FPN
2019 3
Panoptic FPN
2019 3
Spatial Attention Module (ThunderNet)
2019 3
Balanced Feature Pyramid
2019 2
MLFPN
2018 1
FFMv2
2018 1
TridentNet Block
2019 1
MatrixNet
2020 1
FSAF
2019 1
Exact Fusion Model
2019 1
ASFF
2019 1
FFMv1
2018 1
Feature Intertwiner
2019 1