YolOOD: Utilizing Object Detection Concepts for Multi-Label Out-of-Distribution Detection

TL;DR

YolOOD introduces a novel approach that leverages object detection techniques to enhance multi-label out-of-distribution detection, outperforming existing methods on various benchmarks.

Contribution

This work is the first to adapt object detection concepts for multi-label OOD detection, providing a simple yet effective method with minimal modifications.

Findings

YolOOD outperforms state-of-the-art OOD detection methods on benchmark datasets.

Object detection models can be effectively repurposed for multi-label OOD detection.

The proposed approach demonstrates robustness across diverse in-distribution and OOD scenarios.

Abstract

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.