Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness

ArXi:2605.04606v1 Announce Type: cross Traditional one-shot detection methods have addressed the closed-set problem in object detection, but the high cost of data annotation remains a critical challenge. General unsupervised methods generate pseudo boxes without category labels, thus failing to achieve category-aware classification. To overcome these limitations, we propose Reference-based Category Discovery (RefCD), an unsupervised detector that enables category-aware\footnotemark detection without any manually annotated labels.