Abstract: System and method for differentiable networks trainable to learn an optimized query of a 3D model database used for object recognition includes training a first differentiable network configured as a differentiable renderer by generating 2D images from 3D models of a first object of a dissimilar second object while optimizing rendering parameters for producing 2D images by gradient descent of a first triple loss function. Visual variation among the images is maximized. A second differentiable network configured as a convolutional neural network defined by a regression function is trained by generating searchable feature vectors of the 2D images. The feature vectors are determined using optimized neural network parameters determined by gradient descent of a second triple loss function to achieve high correlation to an input image of the first object and low correlation to images of the second object.

Abstract: Anomalies in multiple different scenes or images can be detected and localized in a single training flow of a neural network. In various examples, incremental learning can be applied to a given system or network, such that the system or network can learn the distribution of new scenes in a single training flow. Thus, in some cases, when an anomalous image from a new scene is given as input to the network, the network can detect and localize the anomaly.

Abstract: System and method for differentiable networks trainable to learn an optimized query of a 3D model database used for object recognition includes training a first differentiable network configured as a differentiable renderer by generating 2D images from 3D models of a first object of a dissimilar second object while optimizing rendering parameters for producing 2D images by gradient descent of a first triple loss function. Visual variation among the images is maximized. A second differentiable network configured as a convolutional neural network defined by a regression function is trained by generating searchable feature vectors of the 2D images. The feature vectors are determined using optimized neural network parameters determined by gradient descent of a second triple loss function to achieve high correlation to an input image of the first object and low correlation to images of the second object.

Abstract: A method to account for foreign material in a zone includes the steps of training an object detection model to identify an object using a set of database images of objects on a computer utilizing AI algorithms to create a trained object detection model, receiving an object in an area within a field of view of a camera, distinguishing whether the object is entering the foreign material zone or exiting the foreign material zone, and identifying the object using the trained object detection model. In response to the distinguishing step, the method includes storing the image in a log representing the objects in the foreign material exclusion zone in response to the object being identified by the AI-based trained object detection model when the object is entering he foreign material zone or removing the image from the log when the object is exiting the foreign material zone.