AI RESEARCH
Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark
arXiv CS.CV
•
ArXi:2604.02773v1 Announce Type: new Small object detection (SOD) remains challenging due to extremely limited pixels and ambiguous object boundaries. These characteristics lead to challenging annotation, limited availability of large-scale high-quality datasets, and inherently weak semantic representations for small objects. In this work, we first address the data limitation by