Semi-supervised Object Detection with Unlabeled Data

Nhu-Van Nguyen, Christophe Rigaud, Jean-Christophe Burie

2019

Abstract

Besides the fully supervised object detection, many approaches have tried other training settings such as weakly-supervised learning which uses only weak labels (image-level) or mix-supervised learning which uses few strong labels (instance-level) and many weak labels. In our work, we investigate the semi-supervised learning with few instance-level labeled images and many unlabeled images. Considering the training of unlabeled images as a latent variable model, we propose an Expectation-Maximization method for semi-supervised object detection with unlabeled images. We estimate the latent labels and optimize the model for both classification part and localization part of object detection. Implementing our method on the one-stage object detection model YOLO, we show that like the weakly labeled images, the unlabeled images also can boost the performance of the detector by empirical experimentation on the Pascal VOC dataset.

Paper Citation

in Harvard Style

Nguyen N., Rigaud C. and Burie J. (2019). Semi-supervised Object Detection with Unlabeled Data. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 289-296. DOI: 10.5220/0007345602890296

in Bibtex Style

@conference{visapp19,
author={Nhu-Van Nguyen and Christophe Rigaud and Jean-Christophe Burie},
title={Semi-supervised Object Detection with Unlabeled Data},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP},
year={2019},
pages={289-296},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007345602890296},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 5: VISAPP
TI - Semi-supervised Object Detection with Unlabeled Data
SN - 978-989-758-354-4
AU - Nguyen N.
AU - Rigaud C.
AU - Burie J.
PY - 2019
SP - 289
EP - 296
DO - 10.5220/0007345602890296
PB - SciTePress