无标注条件下实现带类别感知的物体检测
Reference-based Category Discovery: Unsupervised Object Detection with Category Awareness
- 用参考图像与预测框的特征相似性引导类别学习
- 无需标注即可发现潜在类别，准确率优于现有无监督方法
- 支持有无参考图的统一检测框架，适合少样本场景
传统的一次性检测方法解决了物体检测中的闭集问题，但数据标注成本高昂仍是关键挑战。通用无监督方法生成伪框时缺乏类别标签，无法实现类别感知分类。为克服这些局限，我们提出基于参考的类别发现（RefCD），一种无需人工标注的无监督检测器，可实现类别感知检测。该方法利用预测目标与未标注参考图像之间的特征相似性。不同于以往缺乏类别引导的无监督方法或需标注数据的一次性方法，RefCD设计了精心构造的特征相似性损失，显式指导潜在类别特异性特征的学习。此外，RefCD可在无参考图像时支持类别无关检测，构成统一框架。定量与定性分析表明，其在类别感知和类别无关检测上均有效，即使没有类别标签，也能在无监督范式中学习到类别信息。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。