Latest versions of YOLO (starting from YOLOv5[18]) uses an auto-anchor algorithm to find good anchors based on the nature of object sizes in the data set.
Deep learning models have billions of neurons that settle down to some weights after training.
Selecting anchor size plays a vital role in small object detection.
[24] FPN helps to sustain features of small objects against convolution layers.
Various deep learning techniques are available that focus on such object detection problems: e.g., Feature-Fused SSD,[26] YOLO-Z.
[27] Such methods work on "How to sustain features of small objects while they pass through convolution networks."