Abstract
Decision-support systems have been built to assist individuals in categorizing a visual stimulus by presenting the stimulus next to two or more reference images with known category labels. Such systems transform the task of categorization into the task of similarity judgment. Decision-support systems are playing an increasing role in diverse applications such as commercial software products, human-in-the-loop computer vision, and citizen science projects. To explore the capabilities of decision support, Mechanical Turk experiments were devised in which participants make a sequence of similarity judgments between a test exemplar and four reference exemplars. Experiment 1 used rectangles that vary along the dimensions of width and height. Judgments from this experiment were used to select and parameterize a model of human forced-choice selection. This model was used to optimize the choice of reference exemplars for specific categorization tasks. Experiment 2 evaluated implicit classification accuracy on three different categorization tasks, each corresponding to a different decision boundary in the 2D space of rectangles—vertical, horizontal, and diagonal. High classification accuracy (M = 91%, SD = 2%) was achieved even though the three implicit tasks were intermixed and subjects had no awareness that they were performing specific categorization tasks. (From their perspective, the task was similarity judgment.) Through intelligent selection of exemplars, naïve individuals can be guided to make correct classification decisions. Further experiments calibrated the forced-choice selection model—and the reference exemplars chosen based on this model—to individual participants and used more complex and naturalistic stimuli, yielding further encouraging results.
Meeting abstract presented at VSS 2015