Detecting and localising unknown or out-of-distribution (OOD) objects in any scene can be a challenging task in vision, particularly in safety-critical cases involving autonomous systems like automated vehicles or trains. Supervised anomaly segmentation or open-world object detection models depend on training on exhaustively annotated datasets for every domain and still struggle in distinguishing between background and OOD objects. In this work, we present a plug-and-play framework - PRototype-based OOD detection Without Labels (PROWL). It is an inference-based method that does not require training on the domain dataset and relies on extracting relevant features from self-supervised pre-trained models. PROWL can be easily adapted to detect in-domain objects in any operational design domain (ODD) in a zero-shot manner by specifying a list of known classes from this domain. PROWL, as a first zero-shot unsupervised method, achieves state-of-the-art results on the RoadAnomaly and RoadObstacle datasets provided in road driving benchmarks - SegmentMeIfYouCan (SMIYC) and Fishyscapes, as well as comparable performance against existing supervised methods trained without auxiliary OOD data. We also demonstrate its generalisability to other domains such as rail and maritime.
View on arXiv@article{sinhamahapatra2025_2404.07664,
title={ Finding Dino: A Plug-and-Play Framework for Zero-Shot Detection of Out-of-Distribution Objects Using Prototypes },
author={ Poulami Sinhamahapatra and Franziska Schwaiger and Shirsha Bose and Huiyu Wang and Karsten Roscher and Stephan Guennemann },
journal={arXiv preprint arXiv:2404.07664},
year={ 2025 }
}