We address the problem of out-of-distribution (OOD) detection for the task of object detection. We show that residual convolutional layers with batch normalisation produce Sensitivity-Aware FEatures (SAFE) that are consistently powerful for distinguishing in-distribution from out-of-distribution detections. We extract SAFE vectors for every detected object, and train a multilayer perceptron on the surrogate task of distinguishing adversarially perturbed from clean in-distribution examples. This circumvents the need for realistic OOD training data, computationally expensive generative models, or retraining of the base object detector. SAFE outperforms the state-of-the-art OOD object detectors on multiple benchmarks by large margins, e.g. reducing the FPR95 by an absolute 30.6% from 48.3% to 17.7% on the OpenImages dataset.
@article{arxiv.2208.13930,
title = {SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection},
author = {Samuel Wilson and Tobias Fischer and Feras Dayoub and Dimity Miller and Niko Sünderhauf},
journal= {arXiv preprint arXiv:2208.13930},
year = {2023}
}