Abstract: The invention relates to a computer implemented method for training a machine learning model for semantic image segmentation, the method comprising: obtaining training images collectively containing at least three different types of annotations, and training the machine learning model using a loss function, wherein the formulation of the loss function at at least one pixel depends on the types of annotations at the pixel and on the types of annotations within each batch. The invention also relates to a computer implemented method for semantic segmentation making use of the trained machine learning model, and to corresponding systems, computer programs and computer readable media.

Abstract: A flat no-leads package, the flat no-leads package includes a leadframe for electrically connecting an integrated circuit (IC) chip which in a mounted configuration is arranged in a center portion of the flat no-leads package. The leadframe has at least one RF lead pin; and an isolating encapsulation which is at least partially encapsulating the leadframe such that contact surfaces of the leadframe are electrically contactable at least from a bottom side of the flat no-leads package; wherein at least one of the RF lead pin has a first and second contact surfaces. A cross-section of the RF lead pin increases from the first contact surface to the second contact surface both in a horizontal direction and in a direction vertical thereto. Further, a printed circuit board having a flat no-leads package and a measurement device having a flat no-leads package are provided.

Abstract: A flat no-leads package, the flat no-leads package includes a leadframe for electrically connecting an integrated circuit (IC) chip which in a mounted configuration is arranged in a center portion of the flat no-leads package, The leadframe has at least one RF lead pin; and an isolating encapsulation which is at least partially encapsulating the leadframe such that contact surfaces of the leadframe are electrically contactable at least from a bottom side of the flat no-leads package; wherein at least one of the RF lead pin has a first and second contact surfaces. A cross-section of the RF lead pin increases from the first contact surface to the second contact surface both in a horizontal direction and in a direction vertical thereto. Further, a printed circuit board having a flat no-leads package and a measurement device having a flat no-leads package are provided.