Robert Boschgmbh

Laura Beggel

Michael Pfeiffer

Filipe J Cabrita Condessa

Martin Schiegg

Devin T Willmott

Jeremy Zieg Kolter

Robin Hutmacher

Fatemeh Sheikholeslami

Nhung Thi Phuong Ngo

Bernhard Kausler

Methods and systems are disclosed for generating training data for a machine learning model for better performance of the model. A source image is selected from an image database, along with a target image. An image segmenter is utilized with the source image to generate a source image segmentation mask having a foreground region and a background region. The same is performed with the target image to generate a target image segmentation mask having a foreground region and a background region. Foregrounds and backgrounds of the source image and target image are determined based on the masks. The target image foreground is removed from the target image, and the source image foreground is inserted into the target image to create an augmented image having the source image foreground and the target image background. The training data for the machine learning model is updated to include this augmented image.

Data augmentation for domain generalization

A method for detecting an anomalous image among a dataset of images using an Adversarial Autoencoder includes training an Adversarial Autoencoder in a first training with a training dataset of images, with the Adversarial Autoencoder being optimized such that a distribution of latent representations of images of the training dataset of images approaches a predetermined prior distribution and that a reconstruction error of reconstructed images of the training dataset of images is minimized. Subsequently, anomalies are detected in the latent representation and the Adversarial Autoencoder is trained in a second training with the training dataset of images, but taking into account the detected anomalies. The anomalous image among the first dataset of images is detected by the trained Adversarial Autoencoder dependent on at least one of the reconstruction error of the image and a probability density under the predetermined prior distribution.

Method for detecting an anomalous image among a first dataset of images using an adversarial autoencoder

A method for ascertaining whether a series of sensor values contains an anomaly, including the following steps: providing a shapelet and at least one training data series; measuring in each case a distance between the shapelet and the training data series at a plurality of different predefinable positions of the training data series; ascertaining at least one minimal distance from the measured distances and ascertaining at least one change variable for at least one predefinable data point of the shapelet the change variable being ascertained as a function of at least one of the measured distances. A computer program, a device for carrying out the method, and a machine-readable memory element, on which the computer program is stored are also provided.

Method, device and computer program for ascertaining an anomaly

Growing community of inventors

Stuttgart, Germany

Laura Beggel