Abstract: A computer-implemented method for partially supervised image segmentation having improved strong mask generalization includes obtaining, by a computing system including one or more computing devices, a machine-learned segmentation model, the machine-learned segmentation model including an anchor-free detector model and a deep mask head network, the deep mask head network including an encoder-decoder structure having a plurality of layers. The computer-implemented method includes obtaining, by the computing system, input data including tensor data. The computer-implemented method includes providing, by the computing system, the input data as input to the machine-learned segmentation model. The computer-implemented method includes receiving, by the computing system, output data from the machine-learned segmentation model, the output data including a segmentation of the tensor data, the segmentation including one or more instance masks.

Abstract: A device comprises a first transistor, a second transistor, a first contact, and a second contact. The first transistor comprises a first gate structure, first source/drain regions on opposite sides of the first gate structure, and first gate spacers spacing the first gate structure apart from the first source/drain regions. The second transistor comprises a second gate structure, second source/drain regions on opposite sides of the second gate structure, and second gate spacers spacing the second gate structure apart from the second source/drain regions. The first contact forms a first contact interface with one of the first source/drain regions. The second contact forms a second contact interface with one of the second source/drain regions. An area ratio of the first contact interface to top surface the first source/drain region is greater than an area ratio of the second contact interface to top surface of the second source/drain region.

Abstract: Example aspects of the present disclosure are directed to systems and methods that enable weakly-supervised learning of instance segmentation by applying a cut-and-paste technique to training of a generator model included in a generative adversarial network. In particular, the present disclosure provides a weakly-supervised approach to object instance segmentation. In some implementations, starting with known or predicted object bounding boxes, a generator model can learn to generate object masks by playing a game of cut-and-paste in an adversarial learning setup.

Abstract: Example aspects of the present disclosure are directed to systems and methods that enable weakly-supervised learning of instance segmentation by applying a cut-and-paste technique to training of a generator model included in a generative adversarial network. In particular, the present disclosure provides a weakly-supervised approach to object instance segmentation. In some implementations, starting with known or predicted object bounding boxes, a generator model can learn to generate object masks by playing a game of cut-and-paste in an adversarial learning setup.

Abstract: A method for checking a wire connection comprises providing a first current by a first power channel and measuring a first voltage by a first measuring channel when each of a positive terminal of the first measuring channel and a positive terminal of the first power channel is connected to one of positive terminals of batteries and each of a negative terminal of the first measuring channel and a negative terminal of the second measuring channel is connected to one of negative terminals of the batteries after measuring the first voltage, providing a second current by the first power channel and measuring a second voltage by the first measuring channel, and determining whether the first measuring channel and the first power channel are connected to a same battery of the batteries.

Abstract: A method for checking a wire connection comprises providing a first current by a first power channel and measuring a first voltage by a first measuring channel when each of a positive terminal of the first measuring channel and a positive terminal of the first power channel is connected to one of positive terminals of batteries and each of a negative terminal of the first measuring channel and a negative terminal of the second measuring channel is connected to one of negative terminals of the batteries after measuring the first voltage, providing a second current by the first power channel and measuring a second voltage by the first measuring channel, and determining whether the first measuring channel and the first power channel are connected to a same battery of the batteries.