AI RESEARCH
SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection
arXiv CS.CV
•
ArXi:2603.26109v1 Announce Type: new Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts. Benefiting from the emergence of large-scale vision--language pre-trained models, OVOD has nstrated strong zero-shot generalization capabilities. However, when dealing with camouflaged objects, the detector often fails to distinguish and localize objects because the visual features of the objects and the background are highly similar.