ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection

TL;DR

ARUBA introduces a versatile, architecture-agnostic loss function that effectively addresses size imbalance in aerial object detection datasets, leading to improved detection performance across multiple benchmarks.

Contribution

The paper proposes ARUBA, a novel size imbalance-aware loss function that can be integrated with any detection model, enhancing aerial object detection without architectural modifications.

Findings

Consistent performance improvements on HRSC2016, DOTAv1.0, DOTAv1.5, and VisDrone datasets.

Effective handling of size imbalance in aerial datasets.

ARUBA enhances detection accuracy across various models.

Abstract

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 for solving size imbalance are based on architectural changes that utilize multiple scales of images or feature maps for detecting objects of different sizes. We, on the other hand, propose a novel ARchitectUre-agnostic BAlanced Loss (ARUBA) that can be applied as a plugin on top of any object detection model. It follows a neighborhood-driven approach inspired by the ordinality of object size. We evaluate the effectiveness of our approach through comprehensive experiments on aerial datasets such as HRSC2016, DOTAv1.0, DOTAv1.5 and VisDrone and obtain consistent improvement in performance.