Generating Enhanced Negatives for Training Language-Based Object Detectors

arXiv:2401.00094v2 Announce Type: replace
Abstract: The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations. Training such models with a discriminative objective function has proven successful, but requires good positive and negative samples. However, the free-form nature and the open vocabulary of object descriptions make the space of negatives extremely large. Prior works randomly sample negatives or use rule-based techniques to build them. In contrast, we …

arxiv cs.cv detectors language object training type