loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Tobias Brosch and Ahmed Elshaarany

Affiliation: BMW Car IT GmbH, Lise-Meitner-Straße 14, Ulm and Germany

Keyword(s): Heterogeneous Datasets, Object Detection, Deep Learning, Faster R-CNN, Unlabeled Objects.

Abstract: To train an object detection network labeled data is required. More precisely, all objects to be detected must be labeled in the dataset. Here, we investigate how to train an object detection network from multiple heterogeneous datasets to avoid the cost and time intensive task of labeling. In each dataset only a subset of all objects must be labeled. Still, the network shall be able to learn to detect all of the desired objects from the combined datasets. In particular, if the network selects an unlabeled object during training, it should not consider it a negative sample and adapt its weights accordingly. Instead, it should ignore such detections in order to avoid a negative impact on the learning process. We propose a solution for two-stage object detectors like Faster R-CNN (which can probably also be applied to single-stage detectors). If the network detects a class of an unlabeled category in the current training sample it will omit it from the loss-calculation not only in the detection but also in the proposal stage. The results are demonstrated with a modified version of the Faster R-CNN network with Inception-ResNet-v2. We show that the model’s average precision significantly exceeds the default object detection performance. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 35.172.121.218

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Brosch, T. and Elshaarany, A. (2019). Object Detection and Classification on Heterogeneous Datasets. In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-351-3; ISSN 2184-4313, SciTePress, pages 307-312. DOI: 10.5220/0007251903070312

@conference{icpram19,
author={Tobias Brosch. and Ahmed Elshaarany.},
title={Object Detection and Classification on Heterogeneous Datasets},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2019},
pages={307-312},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007251903070312},
isbn={978-989-758-351-3},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Object Detection and Classification on Heterogeneous Datasets
SN - 978-989-758-351-3
IS - 2184-4313
AU - Brosch, T.
AU - Elshaarany, A.
PY - 2019
SP - 307
EP - 312
DO - 10.5220/0007251903070312
PB - SciTePress