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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yichen, Liu, Qiankun, Fu, Ying
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909017092128768
author Li, Yichen
Liu, Qiankun
Fu, Ying
author_facet Li, Yichen
Liu, Qiankun
Fu, Ying
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_04606
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness
Li, Yichen
Liu, Qiankun
Fu, Ying
Computer Vision and Pattern Recognition
Artificial Intelligence
68U
I.4.8
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.
title Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68U
I.4.8
url https://arxiv.org/abs/2605.04606