-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Wilson_2023_ICCV, author = {Wilson, Samuel and Fischer, Tobias and Dayoub, Feras and Miller, Dimity and S\"underhauf, Niko}, title = {SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {23565-23576} }
SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detection
Abstract
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.
Related Material