Uncertainty for Identifying Open-Set Errors in Visual Object Detection

Abstract

Deployed into an open world, object detectors are prone to open-set errors, false positive detections of object classes not present in the training dataset. We propose GMM-Det, a real-time method for extracting epistemic uncertainty from object detectors to identify and reject open-set errors. GMM-Det trains the detector to produce a structured logit space that is modelled with class-specific Gaussian Mixture Models. At test time, open-set errors are identified by their low log-probability under all Gaussian Mixture Models. We test two common detector architectures, Faster R-CNN and RetinaNet, across three varied datasets spanning robotics and computer vision. Our results show that GMM-Det consistently outperforms existing uncertainty techniques for identifying and rejecting open-set detections, especially at the low-error-rate operating point required for safety-critical applications. GMM-Det maintains object detection performance, and introduces only minimal computational overhead. We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to evaluate open-set performance in object detection.

References in corpus (4)

• MMDetection: Open MMLab Detection Toolbox and Benchmark
• A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving
• Can We Trust You? On Calibration of a Probabilistic Object Detector for Autonomous Driving
• Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors

Cited by in corpus (3)

• Open-Set Object Detection Using Classification-free Object Proposal and Instance-level Contrastive Learning
• Towards Robust Object Detection: Bayesian RetinaNet for Homoscedastic Aleatoric Uncertainty Modeling
• Detecting Out-of-distribution Objects Using Neuron Activation Patterns