Dynamic Local and Global Context Exploration for Small Object Detection

The main challenge in small object detection is the limited amount of information available from the objects. As a result of handling insufficient features, context-based methods explore context features on both local and global level as complementary information. However, current methods only investigate local context information within a fixed preset range of neighbors, which makes it difficult to adjust various scenes. Furthermore, extracting global contextual information incurs significant computational costs and introduces noise. In this paper, we propose a novel context-based approach called Dynamic Local and Global Context Exploration (DCE) for small object detection. In DCE, Dynamic Surrounding Search is designed to sense local context information dynamically. A simple and effective module called Semantic Object Relation Enhancement is introduced to enhance proposal features by modeling object relationships. Moreover, we propose Global Feature Supplement to improve detection from a global perspective. Extensive experiments on well-known benchmarks show that our method consistently achieves remarkable improvement over different baselines.