LoANs

  • Recently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also showRecently, deep neural networks have achieved remarkable performance on the task of object detection and recognition. The reason for this success is mainly grounded in the availability of large scale, fully annotated datasets, but the creation of such a dataset is a complicated and costly task. In this paper, we propose a novel method for weakly supervised object detection that simplifies the process of gathering data for training an object detector. We train an ensemble of two models that work together in a student-teacher fashion. Our student (localizer) is a model that learns to localize an object, the teacher (assessor) assesses the quality of the localization and provides feedback to the student. The student uses this feedback to learn how to localize objects and is thus entirely supervised by the teacher, as we are using no labels for training the localizer. In our experiments, we show that our model is very robust to noise and reaches competitive performance compared to a state-of-the-art fully supervised approach. We also show the simplicity of creating a new dataset, based on a few videos (e.g. downloaded from YouTube) and artificially generated data.show moreshow less

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Metadaten
Author details:Christian BartzORCiD, Haojin YangGND, Joseph Bethge, Christoph MeinelORCiDGND
DOI:https://doi.org/10.1007/978-3-030-21074-8_29
ISBN:978-3-030-21074-8
ISBN:978-3-030-21073-1
ISSN:0302-9743
ISSN:1611-3349
Title of parent work (English):Computer Vision – ACCV 2018 Workshops
Subtitle (English):Weakly Supervised Object Detection with Localizer Assessor Networks
Publisher:Springer
Place of publishing:Cham
Publication type:Other
Language:English
Date of first publication:2019/06/19
Completion year:2019
Release date:2021/05/03
Volume:11367
Page number:16
First page:341
Last Page:356
Organizational units:An-Institute / Hasso-Plattner-Institut für Digital Engineering gGmbH
DDC classification:0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme
Peer review:Referiert
Publishing method:Open Access / Green Open-Access