Methods › Computer Vision › Object Detection Models

Object Detection Models

63 methods 2,318 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 3 distinct texts across 62 of the 63 methods here. All are shown, most-carried first (a tie goes to the text carrying Papers with Code's collection boilerplate, then to the longer text); no vote is taken between them.

Text 1, carried by 59 of 63 methods:

Object Detection Models are architectures used to perform the task of object detection. Below you can find a continuously updating list of object detection models.

Text 2, carried by 2 of 63 methods:

Instance Segmentation models are models that perform the task of Instance Segmentation.

Text 3, carried by 1 of 63 methods:

One-Stage Object Detection Models refer to a class of object detection models which are one-stage, i.e. models which skip the region proposal stage of two-stage models and run detection directly over a dense sampling of locations. These types of model usually have faster inference (possibly at the cost of performance). Below you can find a continuously updating list of one-stage object detection models.

Methods

All 63 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.

Faster R-CNN – 499
Mask R-CNN – 420
SSD – 278
YOLOv3 – 258
YOLOv8 You Only Look Once – 254
Detr Detection Transformer – 222
RetinaNet – 209
YOLO You Only Look Once – 108
YOLOv4 – 100
FCOS – 80
YOLOv2 – 55
CenterNet – 47
EfficientDet – 38
Fast R-CNN – 38
Deformable DETR – 35
Cascade R-CNN – 34
R-CNN – 34
R-FCN Region-based Fully Convolutional Network – 32
PANet – 18
Sparse R-CNN – 16
CPN Contour Proposal Network – 14
MDETR – 13
GCNet – 11
RepPoints – 11
VFNet VarifocalNet – 8
CornerNet – 7
SASA Stand-Alone Self Attention – 7
YOLOv1 – 6
Libra R-CNN – 5
RTMDet RTMDet: An Empirical Study of Designing Real-Time Object Detectors – 5
FoveaBox – 4
Grid R-CNN – 4
HTCN Hierarchical Transferability Calibration Network – 4
PP-YOLO – 4
ThunderNet – 4
Dynamic R-CNN – 3
TridentNet – 3
U2-Net – 3
CoVA Context-aware Visual Attention-based (CoVA) webpage object detection pipeline – 2
DAFNe – 2
ExtremeNet – 2
M2Det – 2
MobileDet – 2
NAS-FCOS – 2
PP-YOLOv2 – 2
RFB Net – 2
RPDet – 2
SABL Side-Aware Boundary Localization – 2
YOLOP – 2
C3-AMP Amplified Cross-Stage Partial Block – 1
CentripetalNet – 1
CornerNet-Saccade – 1
CornerNet-Squeeze – 1
DAMO-YOLO – 1
F2DNet Fast Focal Detection Network – 1
H3DNet – 1
MutualGuide Mutual Guidance – 1
PAFNet Paddle Anchor Free Network – 1
PFPNet Parallel Feature Pyramid Network – 1
RetinaMask – 1
SPPF-AMP Amplified Spatial Pyramid Pooling Fast – 1
ScanSSD – 1
HRI pipeline Human Robot Interaction Pipeline – 0