Robert Boschgmbh

William Harris Beluch

Emiel Hoogeboom

Alexandra Lindt

Max Welling

Dan Zhang

Jan Mathias Koehler

Priyank Jaini

Kanil Patel

Didrik Nielsen

Maximilian Autenrieth

Simon Passenheim

A computer-implemented method of training an image analysis model. A coupling layer determines an output vector of integer values from an input vector of integer values. The coupling layer is applied by dividing the input vector into non-overlapping first and second input parts; applying a machine learnable submodel of the coupling layer to the first input part to obtain a submodel output of the machine learnable submodel; sampling a transformation vector from a discrete probability distribution, wherein the discrete probability distribution is parameterized based on the submodel output; determining a second output part based on the second input part and the transformation vector; and combining the first input part and the second output part to obtain the output vector. During backpropagation, a gradient of the sampling of the transformation vector is estimated.

Image analysis model comprising an integer coupling layer

A computer-implemented method of calibrating a trained classification model. The trained classification model is trained to classify input samples according to a plurality of classes and to provide associated prediction probabilities, and includes a plurality of hidden layers and at least one activation layer. The method includes accessing the trained classification model and accessing a plurality of validation samples, each validation sample having a ground-truth label, the ground-truth label indicating a ground-truth class. The method further includes applying the trained classification model to the plurality of validation samples, obtaining, for each validation sample, an output logit vector from a layer of the trained classification model preceding a last activation layer, and training a calibration module. The calibration module is trained to adjust prediction probabilities, the prediction probabilities being derived from the output logit vectors.

Classification model calibration

A method for processing of learning data sets for a classifier. The method includes: processing learning input variable values of at least one learning data set multiple times in a non-congruent manner by one or multiple classifier(s) trained up to an epoch Eso that they are mapped to different output variable values; ascertaining a measure for the uncertainty of these output variable values from the deviations of these output variable values; in response to the uncertainty meeting a predefined criterion, ascertaining at least one updated learning output variable value for the learning data set from one or multiple further output variable value(s) to which the classifier or the classifiers map(s) the learning input variable values after a reset to an earlier training level with epoch E<E.

Processing of learning data sets including noisy labels for classifiers

A computer-implemented method of training an image analysis model. The image analysis model comprises a coupling layer that determines an output vector of discrete values from an input vector of discrete values. First, a machine learnable submodel of the coupling layer is trained to predict a second input part of the coupling layer from a first input part of the coupling layer. Next, the image analysis model is trained. This involves applying the coupling layer by applying the machine learnable submodel to the first input part to obtain a prediction of the second input part; and determining a second output part by applying an invertible mapping to the second input part defined by the prediction of the second input part. The mapping maps a predicted value of an element of the second input part to a fixed value independent from the predicted value.

Image analysis model comprising a discrete coupling layer

A computer-implemented method of training an image generation model. The image generation model comprises an argmax transformation configured to compute a discrete index feature indicating an index of a feature of the continuous feature vector with an extreme value. The image generation model is trained using a log-likelihood optimization. This involves obtaining a value of the index feature for the training image, sampling values of the continuous feature vector given the value of the index feature according to a stochastic inverse transformation of the argmax transformation, and determining a likelihood contribution of the argmax transformation for the log-likelihood based on a probability that the stochastic inverse transformation generates the values of the continuous feature vector given the value of the index feature.

Growing community of inventors

Stuttgart, Germany

William Harris Beluch