Abstract: Approaches are presented for training and using scene graph generators for transfer learning. A scene graph generation technique can decompose a domain gap into individual types of discrepancies, such as may relate to appearance, label, and prediction discrepancies. These discrepancies can be reduced, at least in part, by aligning the corresponding latent and output distributions using one or more gradient reversal layers (GRLs). Label discrepancies can be addressed using self-pseudo-statistics collected from target data. Pseudo statistic-based self-learning and adversarial techniques can be used to manage these discrepancies without the need for costly supervision from a real-world dataset.

Abstract: An improved attaching device for releasably attaching a marking device to a tape measure having a tape measure housing containing a measuring tape, said attaching device comprising a marker retaining arm pivotally mounted on said device and movable between a marking position engageable with a surface to be marked adjacent said measuring tape and a storage position located in a position which is compatible with insertion of said housing into a workbelt pocket.