PDF(Sci-hub)
Abstract：
Non-accidental properties (NAPs) correspond to image properties that are invariant to changes in viewpoint (e.g., straight vs. curved contours) and are distinguished from metric properties (MPs) that can change continuously with in-depth object rotation (e.g., aspect ratio, degree of curvature, etc.). Behavioral and electrophysiological studies of shape processing have demonstrated greater sensitivity to differences in NAPs than in MPs. However, previous work has shown that such sensitivity is lacking in multiple-views models of object recognition such as Hmax. These models typically assume that object processing is based on populations of view-tuned neurons with distributed symmetrical bell-shaped tuning that are modulated at least as much by differences in MPs as in NAPs. Here, we test the hypothesis that unsupervised learning of invariances to object transformations may increase the sensitivity to differences in NAPs vs. MPs in Hmax. We collected a database of video sequences with objects slowly rotating in-depth in an attempt to mimic sequences viewed during object manipulation by young children during early developmental stages. We show that unsupervised learning yields shape-tuning in higher stages with greater sensitivity to differences in NAPs vs. MPs in agreement with monkey IT data. Together, these results suggest that greater NAP sensitivity may arise from experiencing different in-depth rotations of objects.
摘要：
非意外属性(NAP)对应于视点变化不变的图像属性(例如，直vs.弯曲的轮廓)，并且与可以随着深度对象旋转而连续变化的度量属性(MP)(例如，纵横比,弯曲度,等。).形状加工的行为和电生理研究表明，与MP相比，对NAP差异的敏感性更高。然而,以前的工作表明，这种灵敏度是缺乏的多视图模型的对象识别，如Hmax。这些模型通常假设对象处理基于具有分布式对称钟形调谐的视图调谐神经元群体，这些神经元至少受到MP差异的调制，与NAP一样多。这里,我们检验了以下假设：对对象转换的不变性的无监督学习可能会增加对NAP与国会议员在Hmax。我们收集了一个视频序列数据库，其中对象在深度上缓慢旋转，试图模仿幼儿在早期发育阶段在对象操纵过程中观察到的序列。我们表明，无监督学习在更高的阶段产生形状调整，对国家行动方案的差异有更大的敏感性。国会议员同意猴子IT数据。一起,这些结果表明,更高的NAP敏感性可能来自于物体不同的深度旋转.
