Out-of-distribution Object Detection through Bayesian Uncertainty Estimation
This addresses the challenge of unreliable object detection in practical applications where OOD instances are common, offering a scalable solution without high computational costs or synthetic data, though it is incremental as it builds on existing uncertainty-modeling methods.
The paper tackles the problem of out-of-distribution (OOD) object detection by proposing a Bayesian uncertainty estimation method that distinguishes between in-distribution and OOD data using weight parameter sampling from Gaussian distributions based on pre-trained networks, achieving reductions in FPR95 by up to 8.19% and increases in AUROC by up to 13.94% on datasets like BDD100k, VOC, and COCO2017.
The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data. However, in many practical applications, out-of-distribution (OOD) instances are inevitable and usually lead to uncertainty in the results. In this paper, we propose a novel, intuitive, and scalable probabilistic object detection method for OOD detection. Unlike other uncertainty-modeling methods that either require huge computational costs to infer the weight distributions or rely on model training through synthetic outlier data, our method is able to distinguish between in-distribution (ID) data and OOD data via weight parameter sampling from proposed Gaussian distributions based on pre-trained networks. We demonstrate that our Bayesian object detector can achieve satisfactory OOD identification performance by reducing the FPR95 score by up to 8.19% and increasing the AUROC score by up to 13.94% when trained on BDD100k and VOC datasets as the ID datasets and evaluated on COCO2017 dataset as the OOD dataset.