Abstract
An object detector's ability to detect and flag \textit{novel} objects during open-world deployments is critical for many real-world applications. Unfortunately, much of the work in open object detection today is disjointed and fails to adequately address applications that prioritize unknown object recall \textit{in addition to} known-class accuracy. To close this gap, we present a new task called Open-Set Object Detection and Discovery (OSODD) and as a solution propose the Open-Set Regions with ViT features (OSR-ViT) detection framework. OSR-ViT combines a class-agnostic proposal network with a powerful ViT-based classifier. Its modular design simplifies optimization and allows users to easily swap proposal solutions and feature extractors to best suit their application. Using our multifaceted evaluation protocol, we show that OSR-ViT obtains performance levels that far exceed state-of-the-art supervised methods. Our method also excels in low-data settings, outperforming supervised baselines using a fraction of the training data.
Abstract (translated)
物体检测器在开放世界部署中检测和标记新物体的能力对于许多现实应用至关重要。然而，目前开源物体检测中的大部分工作都是不连贯的，没有充分解决优先考虑未知物体召回（除了已知类准确度之外）的应用程序。为了填补这一空白，我们提出了一个名为Open-Set Object Detection and Discovery（OSODD）的新任务，并作为解决方案提出了一种名为Open-Set Regions with ViT features（OSR-ViT）的检测框架。OSR-ViT结合了一个类无关的提议网络和一个强大的基于ViT的分类器。其模块化设计简化了优化，并允许用户轻松交换建议解决方案和特征提取器，以最适合他们的应用程序。通过我们的多维度评估协议，我们证明了OSR-ViT取得的性能水平远远超过了最先进的监督方法。我们的方法在低数据设置中也表现出色，训练数据用量的分数就击败了监督基线。
URL
https://arxiv.org/abs/2404.10865
