Detecting Out-of-distribution Objects Using Neuron Activation Patterns

Abstract

Object detection is essential to many perception algorithms used in modern robotics applications. Unfortunately, the existing models share a tendency to assign high confidence scores for out-of-distribution (OOD) samples. Although OOD detection has been extensively studied in recent years by the computer vision (CV) community, most proposed solutions apply only to the image recognition task. Real-world applications such as perception in autonomous vehicles struggle with far more complex challenges than classification. In our work, we focus on the prevalent field of object detection, introducing Neuron Activation PaTteRns for out-of-distribution samples detection in Object detectioN (NAPTRON). Performed experiments show that our approach outperforms state-of-the-art methods, without the need to affect in-distribution (ID) performance. By evaluating the methods in two distinct OOD scenarios and three types of object detectors we have created the largest open-source benchmark for OOD object detection.

References in corpus (14)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• FCOS: Fully Convolutional One-Stage Object Detection
• MMDetection: Open MMLab Detection Toolbox and Benchmark
• Energy-based Out-of-distribution Detection
• Generalized Out-of-Distribution Detection: A Survey
• Scalability in Perception for Autonomous Driving: Waymo Open Dataset
• BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning
• Deep ReLU Networks Have Surprisingly Few Activation Patterns
• A Survey of Safety and Trustworthiness of Deep Neural Networks: Verification, Testing, Adversarial Attack and Defence, and Interpretability
• Uncertainty for Identifying Open-Set Errors in Visual Object Detection
• Runtime Monitoring Neuron Activation Patterns
• Learning Open-World Object Proposals without Learning to Classify
• Expanding Low-Density Latent Regions for Open-Set Object Detection