Feature Extractors

Edit

Computer Vision • 30 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

Add a Method

Method	Year	Papers
FPN Feature Pyramid Networks for Object Detection	2016	272
TS	2000	76
Bottom-up Path Augmentation Path Aggregation Network for Instance Segmentation	2018	38
PAFPN Path Aggregation Network for Instance Segmentation	2018	37
BiFPN EfficientDet: Scalable and Efficient Object Detection	2019	11
TUM M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	10
NAS-FPN NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection	2019	9
RFB Receptive Field Block Net for Accurate and Fast Object Detection	2017	6
Context Enhancement Module ThunderNet: Towards Real-time Generic Object Detection	2019	5
RFP DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution	2020	4
Panoptic FPN Panoptic Feature Pyramid Networks	2019	3
FSAF Feature Selective Anchor-Free Module for Single-Shot Object Detection	2019	3
SFAM M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	3
Spatial Attention Module (ThunderNet) ThunderNet: Towards Real-time Generic Object Detection	2019	3
Balanced Feature Pyramid Libra R-CNN: Towards Balanced Learning for Object Detection	2019	2
TridentNet Block Scale-Aware Trident Networks for Object Detection	2019	2
MCKERNEL McKernel: A Library for Approximate Kernel Expansions in Log-linear Time	2017	2
FFMv2 M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	1
MatrixNet MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection	2020	1
Feature Intertwiner Feature Intertwiner for Object Detection	2019	1
Streaming Module FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing	2019	1
High-level backbone EfficientPose: Scalable single-person pose estimation	2020	1
Exact Fusion Model CSPNet: A New Backbone that can Enhance Learning Capability of CNN	2019	1
MLFPN M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	1
Low-level backbone EfficientPose: Scalable single-person pose estimation	2020	1
ASFF Learning Spatial Fusion for Single-Shot Object Detection	2019	1
Cross-resolution features EfficientPose: Scalable single-person pose estimation	2020	1
FFMv1 M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	2018	1

Feature Extractors Edit

Methods Add a Method

Feature Extractors

Edit

Methods

Add a Method