Image-Based Out-of-Distribution-Detector Principles on Graph-Based Input Data in Human Action Recognition
| Autor: | Jens Bayer, David Münch, Michael Arens |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Distribution (number theory)
Computer science business.industry Graph based Detector Inference Sample (statistics) 02 engineering and technology Image (mathematics) 020204 information systems 0202 electrical engineering electronic engineering information engineering Action recognition Graph (abstract data type) 020201 artificial intelligence & image processing Artificial intelligence business |
| Zdroj: | Pattern Recognition. ICPR International Workshops and Challenges ISBN: 9783030687625 ICPR Workshops (1) |
| Popis: | Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution. This knowledge is particularly essential in safety-critical environments and tasks e.g. self-driving cars or medical applications. Towards this end, we transfer image-based Out-of-Distribution (OoD)-methods to graph-based data and show the applicability in action recognition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|