Abstract: Systems and methods for constructing and managing a unique road sign knowledge graph across various countries and regions is disclosed. The system utilizes machine learning methods to assist humans when comparing a new sign template with a plurality of stored sign templates to reduce or eliminate redundancy in the road sign knowledge graph. Such a machine learning method and system is also used in providing visual attributes of road signs such as sign shapes, colors, symbols, and the like. If the machine learning determines that the input road sign template is not found in the road sign knowledge graph, the input sign template can be added to the road sign knowledge graph. The road sign knowledge graph can be maintained to add signs templates that are not already in the knowledge graph but are found in real-world by integrating human annotator's feedback during ground truth generation for machine learning.

Abstract: Systems and methods for generating new images for training a machine-learning model are disclosed. Image data is produced regarding an image captured by an image sensor. The image data is altered such that the style of the image (e.g., color, shading, orientation, etc.) is altered. The altered image data is encoded into a first latent space. An image from a database is selected based on its similarity to the altered image and a decoding of the first latent space. Style encodings of the first latent space are extracted to classify a style of the altered image data in a second latent space. New images are then generated utilizing a reconstructor model that combines the two latent spaces. These new images can be used to train an image-recognition model.

Abstract: A computer-implemented method for training a machine-learning network. A computer-implemented method for training a machine-learning network includes generating a frequency spectrum associated with the input data, wherein the generating includes creating the frequency spectrum by applying a frequency domain transformation on the input data, normalizing the frequency spectrum to generate a normalized frequency spectrum, sending the normalized frequency spectrum to a hyper model configured classifying corruptions, utilizing the normalized frequency spectrum as input to the hyper model in order to classify a corruption associated with the input data, updating one or more weights associated with the classifier based on the corruption associated with the input data, and outputting a classification associated with the input data utilizing the classifier with updated weights.

Abstract: Methods and systems are disclosed for quantizing images using machine-learning. A plurality of input images are received from a sensor (e.g., a camera), wherein each input image includes a plurality of pixels. Utilizing an image-to-image machine-learning model, each pixel is assigned a new pixel color. Utilizing a mixer machine-learning model, each new pixel color is converted to one of a fixed number of colors to produce a plurality of quantized images, with each quantized image corresponding to one of the input images. A loss function is determined based on an alignment of each input image with its corresponding quantized image via a pre-trained reference machine-learning model. One or more parameters of the image-to-image machine-learning model and the mixer model are updated based on the loss function. The process repeats, with each iteration updating the parameters of the image-to-image machine-learning model and the mixer model, until convergence, resulting in trained models.

Abstract: Systems and method for machine-learning assisted road sign content prediction and machine learning training is disclosed. A sign detector model processes images or video with road signs. A visual attribute prediction model extracts visual attributes of the sign in the image. The visual attribute prediction model can communicate with a knowledge graph reasoner to validate the visual attribute prediction model by applying various rules to the output of the visual attribute prediction model. A plurality of potential sign candidates are retrieved that match the visual attributes of the image subject to the visual attribute prediction model, and the rules help to reduce the list of potential sign candidates and improve accuracy of the model.

Abstract: Methods and systems are disclosed for quantizing images using machine-learning. A plurality of input images are received from a sensor (e.g., a camera), wherein each input image includes a plurality of pixels. Utilizing an image-to-image machine-learning model, each pixel is assigned a new pixel color. Utilizing a mixer machine-learning model, each new pixel color is converted to one of a fixed number of colors to produce a plurality of quantized images, with each quantized image corresponding to one of the input images. A loss function is determined based on an alignment of each input image with its corresponding quantized image via a pre-trained reference machine-learning model. One or more parameters of the image-to-image machine-learning model and the mixer model are updated based on the loss function. The process repeats, with each iteration updating the parameters of the image-to-image machine-learning model and the mixer model, until convergence, resulting in trained models.

Abstract: Systems and method for machine-learning assisted road sign content prediction and machine learning training is disclosed. A sign detector model processes images or video with road signs. A visual attribute prediction model extracts visual attributes of the sign in the image. The visual attribute prediction model can communicate with a knowledge graph reasoner to validate the visual attribute prediction model by applying various rules to the output of the visual attribute prediction model. A plurality of potential sign candidates are retrieved that match the visual attributes of the image subject to the visual attribute prediction model, and the rules help to reduce the list of potential sign candidates and improve accuracy of the model.

Abstract: Systems and methods for constructing and managing a unique road sign knowledge graph across various countries and regions is disclosed. The system utilizes machine learning methods to assist humans when comparing a new sign template with a plurality of stored sign templates to reduce or eliminate redundancy in the road sign knowledge graph. Such a machine learning method and system is also used in providing visual attributes of road signs such as sign shapes, colors, symbols, and the like. If the machine learning determines that the input road sign template is not found in the road sign knowledge graph, the input sign template can be added to the road sign knowledge graph. The road sign knowledge graph can be maintained to add signs templates that are not already in the knowledge graph but are found in real-world by integrating human annotator's feedback during ground truth generation for machine learning.

Abstract: A system and method relate to providing machine learning predictions with defenses against patch attacks. The system and method include obtaining a digital image and generating a set of location data via a random process. The set of location data include randomly selected locations on the digital image that provide feasible bases for creating regions for cropping. A set of random crops is generated based on the set of location data. Each crop includes a different region of the digital image as defined in relation to its corresponding location data. The machine learning system is configured to provide a prediction for each crop of the set of random crops and output a set of predictions. The set of predictions is evaluated collectively to determine a majority prediction from among the set of predictions. An output label is generated for the digital image based on the majority prediction. The output label includes the majority prediction as an identifier for the digital image.

Abstract: A computer-implemented method for training a machine-learning network. The method includes receiving an input data from a sensor, wherein the input data is indicative of image, radar, sonar, or sound information, generating an input data set utilizing the input data, wherein the input data set includes perturbed data, sending the input data set to a robustifier, wherein the robustifier is configured to clean the input data set by removing perturbations associated with the input data set to create a modified input data set, sending the modified input data set to a pretrained machine learning task, training the robustifier to obtain a trained robustifier utilizing the modified input data set, and in response to convergence of the trained robustifier to a first threshold, output the trained robustifier.

Abstract: A system and method relate to providing machine learning predictions with defenses against patch attacks. The system and method include obtaining a digital image and generating a set of location data via a random process. The set of location data include randomly selected locations on the digital image that provide feasible bases for creating regions for cropping. A set of random crops is generated based on the set of location data. Each crop includes a different region of the digital image as defined in relation to its corresponding location data. The machine learning system is configured to provide a prediction for each crop of the set of random crops and output a set of predictions. The set of predictions is evaluated collectively to determine a majority prediction from among the set of predictions. An output label is generated for the digital image based on the majority prediction. The output label includes the majority prediction as an identifier for the digital image.