Object Detection

R-CNN family, YOLO variants, DETR, anchor-free detectors, and open-vocabulary detection

1.

CenterNet

Center-based keypoint detection using corners as proposals

2.

CornerNet

Anchor-free detection using top-left and bottom-right corner heatmaps

3.

DETR

End-to-end object detection with transformers using bipartite matching

4.

DINO & Grounding DINO WIP

DETR with Improved deNoising anchOr boxes and open-set grounding

5.

ExtremeNet

Object detection via extreme point prediction

6.

InternImage WIP

Large-scale vision foundation model with deformable convolutions

7.

OverFeat

Sliding window + bbox regression + classification

8.

OWLv2 WIP

Open-World Localization with vision-language models

9.

R-CNN Family

R-CNN, SPPNet, Fast R-CNN, Faster R-CNN evolution of region-based detectors

10.

RetinaNet

Focal loss for dense object detection addressing class imbalance

11.

Selective Search WIP

Region proposal algorithm for object detection

12.

SSD WIP

Single Shot MultiBox Detector

13.

Swin Transformer WIP

Hierarchical vision transformer with shifted windows

14.

YOLO-World

Open-vocabulary YOLO with vision-language modeling and RepVL-PAN

15.

YOLO

You Only Look Once — single-shot grid-based object detection

16.

YOLOE WIP

Efficient YOLO variant