YOLOv3 is a real-time, single-stage object detection model that builds on YOLOv2 with several improvements. Improvements include the use of a new backbone network, Darknet-53 that utilises residual connections, or in the words of the author, "those newfangled residual network stuff", as well as some improvements to the bounding box prediction step, and use of three different scales from which to extract features (similar to an FPN).
Source: YOLOv3: An Incremental ImprovementPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 124 | 35.33% |
Real-Time Object Detection | 16 | 4.56% |
Autonomous Driving | 15 | 4.27% |
Classification | 8 | 2.28% |
Instance Segmentation | 7 | 1.99% |
Pedestrian Detection | 6 | 1.71% |
General Classification | 6 | 1.71% |
Object Tracking | 5 | 1.42% |
Autonomous Vehicles | 5 | 1.42% |
Component | Type |
|
---|---|---|
![]() |
Convolutional Neural Networks | |
![]() |
Clustering | |
![]() |
Generalized Linear Models |