Carnegie Mellon University

About: Carnegie Mellon University is a education organization based out in Pittsburgh, Pennsylvania, United States. It is known for research contribution in the topics: Population & Robot. The organization has 36317 authors who have published 104359 publications receiving 5975734 citations. The organization is also known as: CMU & Carnegie Mellon.

What’s the Point: Semantic Segmentation with Point Supervision

Abstract: The semantic image segmentation task presents a trade-off between test time accuracy and training time annotation cost. Detailed per-pixel annotations enable training accurate models but are very time-consuming to obtain; image-level class labels are an order of magnitude cheaper but result in less accurate models. We take a natural step from image-level annotation towards stronger supervision: we ask annotators to point to an object if one exists. We incorporate this point supervision along with a novel objectness potential in the training loss function of a CNN model. Experimental results on the PASCAL VOC 2012 benchmark reveal that the combined effect of point-level supervision and objectness potential yields an improvement of \(12.9\,\%\) mIOU over image-level supervision. Further, we demonstrate that models trained with point-level supervision are more accurate than models trained with image-level, squiggle-level or full supervision given a fixed annotation budget.

Licensing Effect in Consumer Choice

Abstract: Most choices in the real world follow other choices or judgments. The authors show that a prior choice, which activates and boosts a positive self-concept, subsequently licenses the choice of a more self-indulgent option. The authors propose that licensing can operate by committing to a virtuous act in a preceding choice, which reduces negative self-attributions associated with the purchase of relative luxuries. Five studies demonstrate the proposed licensing effect of a prior commitment to a virtuous act on subsequent choice. Consistent with the authors' theory, the preference for an indulgent option diminishes if the licensing task is attributed to an external motivation. The authors also report a mediation analysis in support of their theoretical explanation that the licensing effect operates by providing a temporary boost in the relevant self-concept.

Polymers with Very Low Polydispersities from Atom Transfer Radical Polymerization

Abstract: A radical polymerization process that yields well-defined polymers normally obtained only through anionic polymerizations is reported. Atom transfer radical polymerizations of styrene were conducted with several solubilizing ligands for the copper(I) halides: 4,4′-di-tert-butyl, 4,4′-di-n-heptyl, and 4,4′-di-(5-nonyl)-2,2′-dipyridyl. The resulting polymerizations have all of the characteristics of a living polymerization and displayed linear semilogarithmic kinetic plots, a linear correlation between the number-average molecular weight and the monomer conversion, and low polydispersities (ratio of the weight-average to number-average molecular weights of 1.04 to 1.05). Similar results were obtained for the polymerization of acrylates.