Bootstrapped learning of novel objects
Bootstrapped learning of novel objects
复制标题
DOI：
10.1167/3.6.2
复制
发表时间：
2003-01-01
影响因子：
1.8
通讯作者：
Kersten, D
中科院分区：
文献类型：
--
作者：
Brady, MJ;Kersten, D
在复杂背景中识别熟悉目标是一个具有挑战性的计算问题。摄像机提供了一个特别引人注目的情况，其中对象即使在“平面视图”中也难以检测、识别和分割。“目前的计算方法将联合收割机低级特征与高级模型相结合来识别物体。但如果对象是陌生的呢？一个新的被隐藏的物体提出了一个悖论：视觉系统似乎需要一个物体形状的模型，以便在被隐藏时检测、识别和分割它。但是，视觉系统如何在没有容易分割的样本的情况下构建这样的对象模型呢？一种可能性是，学习识别和分割是机会主义的，因为只有当独特的线索允许从背景中分割对象时，才能学习新对象，例如当目标颜色或运动允许在单个呈现上进行分割时。我们测试了这个想法，并发现，相反，人类观察者可以学习识别和分割一个新的目标形状，即使对于任何给定的训练图像，目标对象是隐藏的。此外，可以在没有精确分割的情况下实现完美的识别。我们称这种从高度模糊的演示中构建形状模型的能力为自举学习。
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.