KIT | KIT-Bibliothek | Impressum | Datenschutz

Double Head Predictor based Few-Shot Object Detection for Aerial Imagery

Wolf, Stefan ORCID iD icon; Meier, Jonas; Sommer, Lars; Beyerer, Jürgen

Abstract (englisch):

Many applications based on aerial imagery rely on ac-curate object detection, which requires a high number of annotated training data. However, the number of annotated training data is often limited. In this paper, we propose a novel few-shot detection method for aerial imagery that aims at detecting objects of unseen classes with only a few annotated examples. For this purpose, we extend the Two-Stage Fine-Tuning Approach (TFA), which achieves state-of-the-art results on common benchmark datasets. We pro-pose a novel annotation sampling and pre-processing strategy to yield a better exploitation of base class annotations and a more stable training. We further apply a modified fine-tuning scheme to reduce the number of missed detections. To prevent loss of knowledge learned during the base training, we introduce a novel double head predictor, yielding the best trade-off in detection accuracy between the novel and base classes. Our proposed Double Head Few-Shot Detection (DH-FSDet) method outperforms state-of-the-art baselines on publicly available aerial imagery datasets. Finally, ablation experiments are performed in or-der to get better insight how few-shot detection in aerial imagery is affected by the selection of base and novel classes. ... mehr

DOI: 10.1109/ICCVW54120.2021.00086
Zitationen: 5
Zitationen: 4
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Fakultät für Informatik – Lehrstuhl IES Beyerer: Interaktive Echtzeitsysteme (Lehrstuhl IES Beyerer: Interaktive Echtzeitsysteme)
Publikationstyp Proceedingsbeitrag
Publikationsmonat/-jahr 10.2021
Sprache Englisch
Identifikator ISBN: 978-1-6654-0192-0
KITopen-ID: 1000141520
Erschienen in IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Montreal, BC, Canada 11th -17th October 2021
Veranstaltung 18th IEEE/CVF International Conference on Computer Vision Workshops (ICCVW 2021), Online, 11.10.2021 – 17.10.2021
Verlag Institute of Electrical and Electronics Engineers (IEEE)
Seiten 721–731
Nachgewiesen in Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page