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

ICLR 2026 Conference Submission9005 Authors

Keywords: Unsupervised, Category-aware Detection, Reference-based

TL;DR: This paper proposes Reference-based Category Discovery (RefCD), an unsupervised detector enables category-aware detection without any manual annotated labels

Abstract: 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 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.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 9005