Scale-Aware Anchor-Free Object Detection via Curriculum Learning for Remote Sensing Images

Accurate detection of multiclass instance objects in remote sensing images (RSIs) is a fundamental but challenging task in the field of aviation and satellite image processing, which plays a crucial role in a wide range of practical applications. Compared with the natural image-based object detection task, RSIs-based object detection still faces two main challenges: 1) The instance objects often present large variations in object size, and they are densely arranged in the given input images; and 2) Complex background distributions around instance objects tend to cause boundary blurring, making it difficult to distinguish instance objects from the background, resulting in undesired feature learning interference. In this article, to address the abovementioned challenges, we propose a novel RSI anchor-free object detection framework that consists of two key components: a cross-channel feature pyramid network (CFPN) and multiple foreground- attentive detection heads (FDHs). First, an anchor-free baseline detector with the CFPN structure is developed to extract features from different convolutional layers and incorporates these multiscale features through parameterized cross-channel learning processes, learning the semantic relations across different scales and levels. Next, each FDH is designed to predict an attention map to enhance the features of the foreground region in RSIs. Furthermore, under this scale-aware anchor-free baseline detector structure, we design a curriculum-style optimization objective that dynamically reweights training instances during the current training epoch, enabling the detector to receive relatively easy instances that match with its current ability. Experimental results on three publicly available object detection datasets demonstrate that the proposed method outperforms existing object detection methods.