FFN: Fountain Fusion Net for Arbitrary-Oriented Object Detection

Arbitrary-oriented object detection (AOOD) is widely used in aerial images because of its efficient object representation. However, current detectors use the over-standardized feature extraction structure, resulting in detectors having no ability to adaptively readjust feature representations of detection units. Meanwhile, we observe that many detection units could not focus on the objects of interest in their receptive field and are easily affected by the background information and interference targets, leading to the weakening of feature expression ability. We call them suboptimal detection units. To address this issue, we propose a novel feature enhancement module called the fountain feature enhancement module (FFEM). FFEM ingeniously uses the fountain-like structure to reconstruct the features of suboptimal detection units, generating fountain features that can automatically condense spatial regional features, which effectively enhance the detectors' overall representation ability. Then, a high-performance AOOD detector called the fountain fusion net (FFN) is proposed with FFEM embedded, and many novel AOOD components are tested for their progressiveness. We validated our FFN and FFEM using three remote sensing datasets DOTA, HRSC2016, and UCAS-AOD as well as one scene text dataset ICDAR 2015. Extensive experiments demonstrate the effectiveness of our proposed method on improving current detectors to achieve state-of-the-art performance based on this novel idea.