基于基础模型，离群目标检测器能学习吗？

Can OOD Object Detectors Learn from Foundation Models?

September 8, 2024

作者: Jiahui Liu, Xin Wen, Shizhen Zhao, Yingxian Chen, Xiaojuan Qi

cs.AI

摘要

由于缺乏开放式OOD数据，OOD（Out-of-distribution）目标检测是一项具有挑战性的任务。受最近文本到图像生成模型（如稳定扩散）的进展启发，我们研究了在大规模开放式数据集上训练的生成模型潜力，用于合成OOD样本，从而增强OOD目标检测。我们引入了SyncOOD，这是一种简单的数据整理方法，利用大型基础模型的能力，从文本到图像生成模型中自动提取有意义的OOD数据。这为模型提供了访问商业基础模型中封装的开放世界知识的能力。然后利用这些合成的OOD样本来增强训练轻量级、即插即用的OOD检测器，从而有效优化内分布（ID）/OOD决策边界。在多个基准测试中进行的大量实验表明，SyncOOD明显优于现有方法，以最少的合成数据使用实现了新的最先进性能。

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.