Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

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

: Wolf, Stefan; Meier, Jonas; Sommer, Lars; Beyerer, Jürgen


Berg, T. ; Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society; Computer Vision Foundation -CVF-:
IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021. Proceedings : 11-17 October 2021, Virtual Event
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2021
ISBN: 978-1-6654-0192-0
ISBN: 978-1-6654-0191-3
International Conference on Computer Vision (ICCV) <18, 2021, Online>
Workshop on Learning to Understand Aerial Images (LUAI) <1, 2021, Online>
Fraunhofer IOSB ()

Many applications based on aerial imagery rely on accurate 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. We provide the source code at