DeepAI AI Chat
Log In Sign Up

Soft Labels for Rapid Satellite Object Detection

by   Matthew Ciolino, et al.

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.


page 2

page 4


Training sound event detection with soft labels from crowdsourced annotations

In this paper, we study the use of soft labels to train a system for sou...

SSN: Soft Shadow Network for Image Compositing

In image compositing tasks, objects from different sources are put toget...

Eliciting and Learning with Soft Labels from Every Annotator

The labels used to train machine learning (ML) models are of paramount i...

Soft-labeling Strategies for Rapid Sub-Typing

The challenge of labeling large example datasets for computer vision con...

Dynamic Supervisor for Cross-dataset Object Detection

The application of cross-dataset training in object detection tasks is c...

Performance of Kriging Based Soft Classification on WiFS/IRS- 1D image using Ground Hyperspectral Signatures

Hard and soft classification techniques are the conventional ways of ima...

SatImNet: Structured and Harmonised Training Data for Enhanced Satellite Imagery Classification

Automatic supervised classification of satellite images with complex mod...