ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection. (arXiv:2210.04574v2 [cs.CV] UPDATED)

Deep neural networks tend to reciprocate the bias of their training dataset.
In object detection, the bias exists in the form of various imbalances such as
class, background-foreground, and object size. In this paper, we denote size of
an object as the number of pixels it covers in an image and size imbalance as
the over-representation of certain sizes of objects in a dataset. We aim to
address the problem of size imbalance in drone-based aerial image datasets.
Existing methods …

architecture aruba arxiv detection loss