A method for training a classifier for image data using learning image data and associated labels, each of the labels including an allocation to one or multiple classes of a predefined classification. In the method, for each data set of learning image data, space-resolved relevance maps are provided, which indicate how relevant which spatial areas of the particular learning image data are for the assessment of the situation shown in the learning image data. From data sets of learning image data and associated relevance maps, learning samples are ascertained; the learning samples are fed to the classifier; and classifier parameters are optimized with the aim that the classifier maps the learning samples to allocations to one or multiple classes which are consistent with the labels of the learning image data from which the learning samples originate.
IMAGE CLASSIFICATION AND ASSOCIATED TRAINING FOR SAFETY-RELEVANT CLASSIFICATION TASKS
2021-12-30
Patent
Elektronische Ressource
Englisch
IPC: | G06K Erkennen von Daten , RECOGNITION OF DATA / B60Q ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL , Anordnung von Signal- oder Beleuchtungsvorrichtungen, deren Einbau oder Halterung oder deren Schaltkreise bei Fahrzeugen allgemein / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Image classification and associated training for safety-relevant classification tasks
Europäisches Patentamt | 2024
|Crowdsearching Training Sets for Image Classification
British Library Conference Proceedings | 2015
|Europäisches Patentamt | 2023
|Technique to extract relevant image features for visual tasks [3299-10]
British Library Conference Proceedings | 1998
|Towards Fast and Robust Adversarial Training for Image Classification
British Library Conference Proceedings | 2021
|