Abstract: Digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. Uncertainty is resolved according to expected characteristics. The label of any image element with an uncertainty above a threshold is replaced with a new label corresponding to a segmentation class based on domain knowledge.

Abstract: A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Abstract: A computer-implement method for training a neural network to detect defects is provided. The method comprises encoding, by an encoder, a real image of an object to produce a first compressed image as a first vector in a latent space, wherein the real image is free of defects. A decoder then generates a reconstructed image from the first vector in the latent space, wherein the reconstructed image is a closest non-anomalous reconstruction of the real image. A discriminator compares the real image and the reconstructed image and determines which image is the real image and which image is the reconstructed image. The encoder also encodes the reconstructed image to produce a second compressed image as a second vector in the latent space.

Abstract: A method for digital image segmentation is provided. The method comprises training a neural network for image segmentation with a labeled training dataset from a first domain, wherein a subset of nodes in the neural net are dropped out during training. The neural network receives image data from a second, different domain. A vector of N values that sum to 1 is calculated for each image element, wherein each value represents an image segmentation class. A label is assigned to each image element according to the class with the highest value in the vector. Multiple inferences are performed with active dropout layers for each image element, and an uncertainty value is generated for each image element. The label of any image element with an uncertainty value above a predefined threshold is replaced with a new label corresponding to the class with the next highest value.

Abstract: A lighting device having an elastomeric band connected to the housing at a first side and surrounding the housing, the elastomeric band seated in a channel surrounding the housing in a first configuration, the elastomeric band removable from the channel and capable of wrapping around a structure to which the lighting device is to be secured, the elastomeric band hooking over a retention tab located on the housing on a side opposite the elastomeric band connection side to secure the lighting device to the structure.