Methods › Computer Vision › One-Stage Object Detection Models

One-Stage Object Detection Models

21 methods 919 papers tagged archive 2025-07-28

The archive attaches this collection's text per method and the copies differ: 2 distinct texts across 21 of the 21 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 18 of 21 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 3 of 21 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 21 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.

SSD – 278
YOLOv3 – 258
RetinaNet – 209
YOLOv4 – 100
FCOS – 80
YOLOv2 – 55
CenterNet – 47
EfficientDet – 38
YOLOX – 33
CPN Contour Proposal Network – 14
CornerNet – 7
YOLOv1 – 6
FoveaBox – 4
PP-YOLO – 4
ExtremeNet – 2
M2Det – 2
RFB Net – 2
RetinaNet-RS – 2
YOLOP – 2
CornerNet-Saccade – 1
RetinaMask – 1