The present disclosure relates to an object selection system that accurately detects and optionally automatically selects user-requested objects (e.g., query objects) in digital images. For example, the object selection system builds and utilizes an object selection pipeline to determine which object detection neural network to utilize to detect a query object based on analyzing the object class of a query object. In particular, the object selection system can identify both known object classes as well as objects corresponding to unknown object classes.

A system and method for providing object-level driver attention reasoning with a graph convolution network that include receiving image data associated with a plurality of image clips of a surrounding environment of a vehicle and determining anchor objectness scores and anchor importance scores associated with relevant objects included within the plurality of image clips. The system and method also include analyzing the anchor objectness scores and anchor importance scores associated with relevant objects and determining top relevant objects with respect to an operation of the vehicle. The system and method further include passing object node features and edges of an interaction graph through the graph convolution network to update features of each object node through interaction with other object nodes and determining importance scores for the top relevant objects.

A computer system is provided that is programmed to select feature sets from a large number of features. Features for a set are selected based on metagradient information returned from a machine learning process that has been performed on an earlier selected feature set. The process can iterate until a selected feature set converges or otherwise meets or exceeds a given threshold.

Methods and systems for determining a displacement of a peripheral device are provided. In one example, a peripheral device comprises: an image sensor, and a hardware processor configured to: control the image sensor to capture a first image of a surface when the peripheral device is at a first location on the surface, the first image comprising a feature of the first location of the surface; execute a trained machine learning model using data derived from the first image to estimate a displacement of the feature between the first image and a reference image captured at a second location of the surface; and determine a displacement of the peripheral device based on the estimated displacement of the feature.

The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.

The invention relates to a system for detecting objects in a digital image. The system comprises a neural network which is configured to generate candidate windows indicating object locations, and to generate for each candidate window a score representing the confidence of detection. Generating the scores comprises: generating a latent representation for each candidate window, updating the latent representation of each candidate window based on the latent representation of neighboring candidate windows, and generating the score for each candidate window based on its updated latent representation The invention further relates to a system for rescoring object detections in a digital image and to methods of detecting objects and rescoring objects.

Techniques facilitating causal reasoning for explanation of model predictions are provided. A system can generate one or more explanations of a machine learning model prediction. The one or more explanations can be based on causal relationships determined between feature data of a set of feature data and based on dataset point samples around a trace associated with the causal relationships.

One or more embodiments of the present disclosure include systems and methods that use neural architecture fusion to learn how to combine multiple separate pre-trained networks by fusing their architectures into a single network for better computational efficiency and higher accuracy. For example, a computer implemented method of the disclosure includes obtaining multiple trained networks. Each of the trained networks may be associated with a respective task and has a respective architecture. The method further includes generating a directed acyclic graph that represents at least a partial union of the architectures of the trained networks. The method additionally includes defining a joint objective for the directed acyclic graph that combines a performance term and a distillation term. The method also includes optimizing the joint objective over the directed acyclic graph.

Aspects of the invention include a computer-implemented method that receives, by a processor, an ensemble decision tree and generates, by the processor, native code from the ensemble decision tree. The method compiles, by the processor, the native code into machine language and scores, by the processor, the execution time of the native code. The method dynamically reoptimizes, by the processor, portions of the native code corresponding to the most traversed portion of the ensemble decision tree.

A plurality of fault conditions are detected on a communication network onboard a vehicle. The detected fault conditions, a fault condition importance, environment conditions, and a vehicle operation mode are input to a neural network that outputs rankings for respective detected fault conditions. The neural network is trained by determining a loss function based on a maximum likelihood principle that determines a probability distribution that ranks the detected fault conditions. The vehicle is operated based on the rankings of the fault conditions.