Feature Extractors

Edit

Computer Vision • 33 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).

Subcategories

1 Feature Pyramid Blocks

Methods

Add a Method

Method	Year	Papers
FPN Feature Pyramid Networks for Object Detection	2016	521
TS	2000	191
Bottom-up Path Augmentation Path Aggregation Network for Instance Segmentation	2018	111
PAFPN Path Aggregation Network for Instance Segmentation	2018	111
DLA Deep Layer Aggregation	2017	76
BiFPN EfficientDet: Scalable and Efficient Object Detection	2019	38
TUM M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	37
NEAT NEAT: Neural Attention Fields for End-to-End Autonomous Driving	2021	15
NAS-FPN NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection	2019	11
RFP DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution	2020	10
RFB Receptive Field Block Net for Accurate and Fast Object Detection	2017	7
Context Enhancement Module ThunderNet: Towards Real-time Generic Object Detection	2019	6
FSAF Feature Selective Anchor-Free Module for Single-Shot Object Detection	2019	6
Balanced Feature Pyramid Libra R-CNN: Towards Balanced Learning for Object Detection	2019	6
SFAM M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	4
TridentNet Block Scale-Aware Trident Networks for Object Detection	2019	4
Spatial Attention Module (ThunderNet) ThunderNet: Towards Real-time Generic Object Detection	2019	4
FPG Feature Pyramid Grids	2020	4
Panoptic FPN Panoptic Feature Pyramid Networks	2019	3
FFMv1 M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	2
MatrixNet MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection	2020	2
FFMv2 M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	2
Cross-resolution features EfficientPose: Scalable single-person pose estimation	2020	2
Low-level backbone EfficientPose: Scalable single-person pose estimation	2020	2
MCKERNEL McKernel: A Library for Approximate Kernel Expansions in Log-linear Time	2017	2
MLFPN M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	2
Exact Fusion Model CSPNet: A New Backbone that can Enhance Learning Capability of CNN	2019	1
ASFF Learning Spatial Fusion for Single-Shot Object Detection	2019	1
Feature Intertwiner Feature Intertwiner for Object Detection	2019	1
High-level backbone EfficientPose: Scalable single-person pose estimation	2020	1
Streaming Module FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing	2019	1

Feature Extractors Edit

Methods Add a Method

Feature Extractors

Edit

Methods

Add a Method