Abstract: Methods for fine-tuning a convolutional neural network of a Text-To-Image Diffusion Model within a context of recognizing defects of manufactured products within images of those products are disclosed. Images of manufactured images that have various scratches, dents, or other defects are provided to the model along with a word or phrase indicating that there is a defect. The model then learns to identify the portion of the overall image that includes the defect. The learning of this type of task is based on the use of segmentation masks that correspond to the images, which are then used along with cross-attention maps of the model in order to calculate an average defect mask loss parameter of the model. By computing this parameter and applying it when updating weights of the model, the model can be fine-tuned to detect defects of manufactured products.

Abstract: A method for training a control policy for manipulating an object. For each of one or more objects in each of one or more scenes, receiving an input data element including image data representing a shape of the object to be manipulated and its position in the scene, generating, for each input data element, one or more training data elements by generating augmentations of the image data and pseudo-labels for the augmented image data according to a semi-supervised learning scheme and training the control policy using the generated training data elements.

Abstract: A method for adapting a machine learning model to a changed control situation. The method includes detecting sensor data elements in the changed control situation; for each ascertained sensor data element generating multiple augmentations of the sensor data element; generating, for each augmentation, a respective output by means of a first instance of the machine learning model; ascertaining a target output for the sensor data element by combining the generated outputs; and ascertaining a loss between an output of a second instance for the sensor data element and the ascertained target output; and adapting the second instance of the machine learning model in order to reduce a total loss, which contains the ascertained losses.

Abstract: A method for training a machine learning model for controlling a robot. The method includes, for each training data element of a set of training data elements, wherein each training data element comprises training input information about the location of surface points of a respective object and one or more possible approach directions of the robot for manipulating the object, ascertaining, via the machine learning model, one or more contact points, ascertaining, via the machine learning model, weighting parameter values of a mixture distribution of spherical distributions for the approach direction, and training the machine learning model to reduce a loss that contains an approach-direction loss component per training data element and per possible approach direction.