Methods > Computer Vision

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).

METHOD YEAR PAPERS
FPN
2016 239
TS
2000 68
Bottom-up Path Augmentation
2018 30
PAFPN
2018 29
TUM
2018 10
NAS-FPN
2019 9
BiFPN
2019 9
RFB
2017 5
Context Enhancement Module
2019 5
Spatial Attention Module (ThunderNet)
2019 3
SFAM
2018 3
Panoptic FPN
2019 3
RFP
2020 3
TridentNet Block
2019 2
Balanced Feature Pyramid
2019 2
MCKERNEL
2017 2
Feature Intertwiner
2019 1
FSAF
2019 1
FFMv2
2018 1
FFMv1
2018 1
MatrixNet
2020 1
Exact Fusion Model
2019 1
MLFPN
2018 1
ASFF
2019 1
Cross-resolution features
2020 1
High-level backbone
2020 1
Low-level backbone
2020 1
Streaming Module
2019 1