Search papers, labs, and topics across Lattice.
This paper introduces Reference-based Category Discovery (RefCD), an unsupervised object detection framework that learns category-aware detection by leveraging feature similarity between predicted objects and unlabeled reference images. RefCD employs a novel feature similarity loss to guide the learning of category-specific features without requiring manual annotations. Experiments demonstrate that RefCD effectively learns category information in an unsupervised manner, achieving both category-aware and category-agnostic detection.
Unsupervised object detection can now achieve category awareness, bridging the gap with supervised methods without needing any labeled data.
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[1] detection without any manually annotated labels. It leverages feature similarity between predicted objects and unlabeled reference images. Unlike previous unsupervised methods that lack category guidance and one-shot methods which require labeled data, RefCD introduces a carefully designed feature similarity loss to explicitly guide the learning of potential category-specific features. Additionally, RefCD supports category-agnostic detection without reference images, serving as a unified framework. Comprehensive quantitative and qualitative analysis of category-aware and category-agnostic detection results demonstrates its effectiveness, and RefCD can learn category information in an unsupervised paradigm even without category labels.
