Abstract: A method for recognizing at least one object in at least one input image. In the method, a template image of the object is processed by a first convolutional neural network (CNN) to form at least one template feature map; the input image is processed by a second CNN to form at least one input feature map; the at least one template feature map is compared to the at least one input feature map; it is evaluated from the result of the comparison whether and possibly at which position the object is contained in the input image, the convolutional neural networks each containing multiple convolutional layers, and at least one of the convolutional layers being at least partially formed from at least two filters, which are convertible into one another by a scaling operation.

Abstract: An apparatus and a computer implemented method for unsupervised representation learning. The method includes: providing an input data set comprising samples of a first domain and samples of a second domain; providing a reference assignment between pairs of one sample from the first domain and one sample from the second domain; providing an encoder that is configured to map a sample of the input data set depending on at least one parameter of the encoder to an embedding; providing a similarity kernel for determining a similarity between embeddings; determining with the encoder embeddings of samples from the first domain and embeddings of samples from the second domain; determining with the similarity kernel similarities for pairs of one embedding of a sample from the first domain and one embedding of a sample from the second domain; determining at least one parameter of the encoder depending on a loss.

Abstract: A device and computer-implemented method for object tracking. The method comprises providing a sequence of digital images, determining a sequence of relational graph embeddings, wherein a first relational graph embedding of the sequence comprises a first object embedding representing a first object in a first digital image of the sequence of digital images, wherein the first relational graph embedding comprises a first relation embedding of a relation for the first object embedding, wherein the first relation embedding relates the first object embedding to embeddings representing other objects of the first digital image in the first relational graph embedding and to embeddings in a second relational graph embedding of the sequence that represent objects of a second digital image of the sequence of digital images.

Abstract: A system and computer-implemented method for training a machine learnable model to estimate a relative scale of objects in an image. A feature extractor and a scale estimator comprising a machine learnable model part are provided. The feature extractor may be pretrained, while the scale estimator may be trained by the system and method to transform feature maps generated by the feature extractor into relative scale estimates of objects. For that purpose, the scale estimator may be trained on training data in a specific yet non-supervised manner which may not require scale labels. During inference, the scale estimator may be applied to several image patches of an image. The resulting patch-level scale estimates may be combined into a scene geometry map which may be indicative of a geometry of a scene depicted in the image.

Abstract: A computer-implemented method for training a scale-equivariant convolutional neural network. The scale-equivariant convolutional neural network is configured to determine an output signal characterizing a classification of an input image of the scale-equivariant convolutional neural network. The scale-equivariant convolutional neural network includes a convolutional layer. The convolutional layer is configured to provide a convolution output based on a plurality of steerable filters of the convolutional layer and a convolution input. The convolution input is based on the input image and the steerable filters are determined based on a plurality of basis filters. The method for training includes training the plurality of basis filters.

Abstract: A method for recognizing at least one object in at least one input image. In the method, a template image of the object is processed by a first convolutional neural network (CNN) to form at least one template feature map; the input image is processed by a second CNN to form at least one input feature map; the at least one template feature map is compared to the at least one input feature map; it is evaluated from the result of the comparison whether and possibly at which position the object is contained in the input image, the convolutional neural networks each containing multiple convolutional layers, and at least one of the convolutional layers being at least partially formed from at least two filters, which are convertible into one another by a scaling operation.

Abstract: A method of one shot joint instance and pose recognition in an artificial neural network is presented. The method includes receiving a reference instance of a reference object from a reference image. The reference object has a first identity and a first pose in the reference instance. The method also includes generating a first orbit of the reference object comprising multiple additional poses including a second pose for the reference object. The method further includes recognizing a second instance of an example object from an example image. The example object has the first identity and the second pose in the second instance. The method still further includes recognizing the second pose and first identity of the example object based on comparing the first orbit with a second orbit of the example object.

Abstract: A computer-implemented method for processing sensor data using a convolutional network. The method includes: processing the sensor data using several successive layers of the convolutional network, which has a convolution filter layer that receives an input matrix having input data values, implements a first filter matrix that is defined by a sum, weighted with a first weighting, of basic filter functions, calculates a second weighting from the first weighting by applying to the first weighting, for a respective value of a transformation parameter, a transformation formula that is parameterized by the transformation parameter, for each second weighting, ascertains a respective second filter matrix by calculating a sum, weighted with the second weighting, of the basic filter functions, and convolutes the input matrix with the first filter matrix and with each of the second filter matrices, so that for each filter matrix, an output matrix having output data values is generated.

Abstract: A method of tracking an object includes performing a hybrid search over a sequence of frames. The hybrid search includes periodically performing a global search on selected frames of the sequence of frames and performing a local search on frames between the selected frames of the global search. The method also includes updating a similarity function based on a result of the hybrid search. The method further includes tracking the object based on the hybrid search.