A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.

A system is provided for unsupervised cross-domain image generation relative to a first and second image domain that each include real images. A first generator generates synthetic images similar to real images in the second domain while including a semantic content of real images in the first domain. A second generator generates synthetic images similar to real images in the first domain while including a semantic content of real images in the second domain. A first discriminator discriminates real images in the first domain against synthetic images generated by the second generator. A second discriminator discriminates real images in the second domain against synthetic images generated by the first generator. The discriminators and generators are deep neural networks and respectively form a generative network and a discriminative network in a cyclic GAN framework configured to increase an error rate of the discriminative network to improve synthetic image quality.

An unlabelled or partially labelled target dataset is modelled with a machine learning model for classification (or regression). The target dataset is processed by the machine learning model; a subgroup of the target dataset is prepared for presentation to a user for labelling or label verification; label verification or user re-labelling or user labelling of the subgroup is received; and the updated target dataset is re-processed by the machine learning model. User labelling or label verification combined with modelling an unclassified or partially classified target dataset with a machine learning model aims to provide efficient labelling of an unlabelled component of the target dataset.

The systems, methods, and computer programs disclosed herein relate to detecting and/or recognizing a tissue type in an image of the tissue using machine learning techniques.

In general, techniques are described for unsupervised domain adaptation of models with pseudo-label curation. In an example, a method includes generating a plurality of pseudo-labels for a dataset of unlabeled data using a source machine learning model; estimating a reliability of each pseudo-label of the plurality of pseudo-labels using one or more reliability measures; selecting a subset of the plurality of pseudo-labels having estimated reliabilities that satisfy a reliability threshold; and training, using one or more curriculum learning techniques, a target machine learning model starting with the selected subset of the plurality of pseudo-labels and the corresponding unlabeled data.

A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.

Methods and systems for training a neural network model include augmenting an original training dataset to generate an augmented training dataset, by applying an image artifact to a portion of an original image of the original dataset to generate an artifact image. A target image is generated corresponding to the artifact image by deleting labels from the target image at the position of the artifact. A neural network model is trained using the augmented training dataset and the corresponding target image, the neural network model including a first output that identifies artifact regions and other outputs identifying objects.

A landmark detection system can more accurately detect landmarks in images using a detection scheme that penalizes for dispersion parameters, such as variance or scale. The landmark detection system can be trained using both labeled and unlabeled training data in a semi-supervised approach. The landmark detection system can further implement tracking of an object across multiple images using landmark data.

A method includes obtaining an authentic image of an assembly and a boundary label provided with the authentic image. The boundary label is associated with a selected region of the authentic image depicting a selected object. The method includes generating an augmented image based on the authentic image and an augmentation model employing one or more augmentation parameters, defining a model boundary label on a blank image at a region that correlates with the selected region of the authentic image, generating an augmented blank image based on the one or more augmentation parameters employed for the augmented image, identifying, as an augmented boundary label associated with augmented image, the model boundary label in the augmented blank image, and outputting an augmented image data, wherein the augmented image data incudes data indicative of the augmented image and of the augmented boundary label.

An object region segmentation device and an object region segmentation method thereof are provided. The object region segmentation device includes a processor and storage. The storage stores a deep-learning network model for segmenting an object region in an image. The deep-learning network model includes a first network model for generating a pseudo label, a second network model for generating a confidence map for the pseudo label, and a third network model for segmenting the object region in the image. The processor inputs an unlabeled image to the first network model to generate the pseudo label, inputs the pseudo label to the second network model to generate the confidence map, and trains the third network model using a pseudo label corresponding to at least one pixel, a confidence level of which is greater than or equal to a threshold, on the confidence map.