# Soft Labels for Rapid Satellite Object Detection

Source: [Soft Labels for Rapid Satellite Object Detection](<https://www.sota2.com/research/paper/68fa6e771e209131cea400ba>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:57:53.973Z

Authors: Matthew Ciolino, Grant Rosario, David Noever

Published: 2022-12-01T15:23:13.000Z

## Abstract

Soft labels in image classification are vector representations of an image's true classification. In this paper, we investigate soft labels in the context of satellite object detection. We propose using detections as the basis for a new dataset of soft labels. Much of the effort in creating a high-quality model is gathering and annotating the training data. If we could use a model to generate a dataset for us, we could not only rapidly create datasets, but also supplement existing open-source datasets. Using a subset of the xView dataset, we train a YOLOv5 model to detect cars, planes, and ships. We then use that model to generate soft labels for the second training set which we then train and compare to the original model. We show that soft labels can be used to train a model that is almost as accurate as a model trained on the original data.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2212.00585>)

[PDF](<https://arxiv.org/pdf/2212.00585.pdf>)