OoDIS: Anomaly Instance Segmentation and Detection Benchmark

Safe navigation of self-driving cars and robots requires a precise understanding of their environment. Training data for perception systems cannot cover the wide variety of objects that may appear during deployment. Thus, reliable identification of unknown objects, such as wild animals and untypical obstacles, is critical due to their potential to cause serious accidents. Significant progress in semantic segmentation of anomalies has been facilitated by the availability of out-of-distribution (OOD) benchmarks. However, a comprehensive understanding of scene dynamics requires the segmentation of individual objects, and thus the segmentation of instances is essential. Development in this area has been lagging, largely due to the lack of dedicated benchmarks. The situation is similar in object detection. While there is interest in detecting and potentially tracking every anomalous object, the availability of dedicated benchmarks is clearly limited. To address this gap, this work extends some commonly used anomaly segmentation benchmarks to include the instance segmentation and object detection tasks. Our evaluation of anomaly instance segmentation and object detection methods shows that both of these challenges remain unsolved problems. We provide a competition and benchmark website under https://vision.rwth-aachen.de/oodis.

Authors

• Alexey Nekrasov 0001
• Rui Zhou
• Miriam Ackermann
• Alexander Hermans
• Bastian Leibe
• Matthias Rottmann

Keywords

• Instance segmentation
• Training
• Visualization
• Navigation
• Annotations
• Training data
• Object detection
• Benchmark testing
• Reliability
• Robots
• Anomaly Detection
• Segmentation Method
• Semantic Segmentation
• Segmentation Task
• Individual Objects
• Object Segmentation
• Object Detection Methods
• Segmentation Detection
• Robot Navigation
• Unknown Objects
• Instance Segmentation Methods
• Training Set
• Validation Set
• False Positive Rate
• Bounding Box
• Segmentation Model
• Average Precision
• Anomaly Score
• Small Objects
• Auxiliary Data
• Ambiguous Regions
• Sheep Flocks
• Segmentation Accuracy
• Open Set
• Evaluation Protocol