Brady Mark J, Kersten Daniel
Department of Psychology, University of Minnesota, Minneapolis, MN, USA.
J Vis. 2003;3(6):413-22. doi: 10.1167/3.6.2.
Recognition of familiar objects in cluttered backgrounds is a challenging computational problem. Camouflage provides a particularly striking case, where an object is difficult to detect, recognize, and segment even when in "plain view." Current computational approaches combine low-level features with high-level models to recognize objects. But what if the object is unfamiliar? A novel camouflaged object poses a paradox: A visual system would seem to require a model of an object's shape in order to detect, recognize, and segment it when camouflaged. But, how is the visual system to build such a model of the object without easily segmentable samples? One possibility is that learning to identify and segment is opportunistic in the sense that learning of novel objects takes place only when distinctive clues permit object segmentation from background, such as when target color or motion enables segmentation on single presentations. We tested this idea and discovered that, on the contrary, human observers can learn to identify and segment a novel target shape, even when for any given training image the target object is camouflaged. Further, perfect recognition can be achieved without accurate segmentation. We call the ability to build a shape model from high-ambiguity presentations bootstrapped learning.
在杂乱背景中识别熟悉物体是一个具有挑战性的计算问题。伪装提供了一个特别突出的例子，即使物体处于“清晰视野”中，也很难被检测、识别和分割。当前的计算方法将低级特征与高级模型相结合来识别物体。但是，如果物体是不熟悉的呢？一个新的伪装物体带来了一个悖论：视觉系统似乎需要一个物体形状模型，以便在物体被伪装时对其进行检测、识别和分割。但是，视觉系统如何在没有易于分割的样本的情况下构建这样一个物体模型呢？一种可能性是，学习识别和分割是机会主义的，即只有当独特线索允许从背景中分割出物体时，才会学习新物体，例如当目标颜色或运动在单次呈现时能够实现分割。我们测试了这个想法，结果发现，相反，人类观察者可以学会识别和分割新的目标形状，即使对于任何给定的训练图像，目标物体都是被伪装的。此外，无需精确分割就能实现完美识别。我们将从高度模糊的呈现中构建形状模型的能力称为自引导学习。
