CNN(Convolution Neural Network)
The state-of-the-art(SOTA) methods can be categorized into two main types
> One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet.
> Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.
★Object Detection (物体検出)
2015 Fast R-CNNとRoI pooling
2015 Faster R-CNNとRegion Proposal Networks
2015 YOLOとOne stage detector
2017 RetinaNetとFocal Loss
2018 M2DetとMulti-Level FPN
2019 Cascade R-CNN
2019 CBNet