用生成模型合成异常样本，提升目标检测的泛化能力。
Can OOD Object Detectors Learn from Foundation Models?
- 利用文本生成图像模型自动提取有意义的异常数据。
- 仅用少量合成数据就实现最优检测性能。
- 适合关注模型鲁棒性与开放世界检测的研究者。
由于缺乏开放集的异常数据，分布外（OOD）目标检测极具挑战。受近期文本到图像生成模型（如 Stable Diffusion）进展启发，本文研究了大规模开放集训练的生成模型在合成 OOD 样本方面的潜力，以增强 OOD 目标检测能力。提出 SyncOOD——一种简单高效的数据整理方法，利用大型基础模型从文本生成图像模型中自动提取有意义的 OOD 样本，使检测器获得现成基础模型中封装的开放世界知识。这些合成的 OOD 样本被用于增强一个轻量级、即插即用的 OOD 检测器训练，从而有效优化分布内（ID）与分布外（OOD）的决策边界。在多个基准测试上的大量实验表明，SyncOOD 显著优于现有方法，在极少合成数据使用条件下达到新的最佳性能。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) object detection is a challenging task due to the absence of open-set OOD data. Inspired by recent advancements in text-to-image generative models, such as Stable Diffusion, we study the potential of generative models trained on large-scale open-set data to synthesize OOD samples, thereby enhancing OOD object detection. We introduce SyncOOD, a simple data curation method that capitalizes on the capabilities of large foundation models to automatically extract meaningful OOD data from text-to-image generative models. This offers the model access to open-world knowledge encapsulated within off-the-shelf foundation models. The synthetic OOD samples are then employed to augment the training of a lightweight, plug-and-play OOD detector, thus effectively optimizing the in-distribution (ID)/OOD decision boundaries. Extensive experiments across multiple benchmarks demonstrate that SyncOOD significantly outperforms existing methods, establishing new state-of-the-art performance with minimal synthetic data usage.
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。