YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection
It addresses a critical safety issue for deployed AI systems by improving OOD detection in multi-label scenarios, which is an underexplored area.
The paper tackles out-of-distribution (OOD) detection in multi-label classification, a common real-world task, by proposing YolOOD, which adapts object detection concepts to achieve superior performance compared to state-of-the-art methods on benchmark datasets.
Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task, a more common real-world use case, remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) in images that contain multiple objects belonging to different class categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.