Do viewpoint-dependent mechanisms generalize across members of a class?

被引:50
作者
Tarr, MJ
Gauthier, I
机构
[1] Brown Univ, Dept Cognit & Linguist Sci, Providence, RI 02912 USA
[2] Yale Univ, Dept Psychol, New Haven, CT 06520 USA
基金
美国国家科学基金会;
关键词
class generalization; image-based recognition; viewpoint-specific representation;
D O I
10.1016/S0010-0277(98)00023-7
中图分类号
B84 [心理学];
学科分类号
04 ; 0402 ;
摘要
Evidence for viewpoint-specific image-based object representations have been collected almost entirely using exemplar-specific recognition tasks. Recent results, however, implicate image-based processes in more categorical tasks, for instance when objects contain qualitatively different 3D parts. Although such discriminations approximate class-level recognition, they do not establish whether image-based representations can support generalization across members of an object class. This issue is critical to any theory of recognition, in that one hallmark of human visual competence is the ability to recognize unfamiliar instances of a familiar class. The present study addresses this question by testing whether viewpoint-specific representations for some members of a class facilitate the recognition of other members of that class. Experiment 1 demonstrates that familiarity with several members of a class of novel 3D objects generalizes in a viewpoint-dependent manner to cohort objects from the same class. Experiment 2 demonstrates that this generalization is based on the degree of familiarity and the degree of geometrical distinctiveness for particular viewpoints. Experiment 3 demonstrates that this generalization is restricted to visually-similar objects rather than all objects learned in a given context. These results support the hypothesis that image-based representations are viewpoint dependent, but that these representations generalize across members of perceptually-defined classes. More generally, these results provide evidence for a new approach to image-based recognition in which object classes are represented as clusters of visually-similar viewpoint-specific representations. (C) 1998 Elsevier Science B.V. All rights reserved.
引用
收藏
页码:73 / 110
页数:38
相关论文
共 62 条
[1]   ROLE OF VISUAL AND SEMANTIC CODES IN OBJECT NAMING [J].
BARTRAM, DJ .
COGNITIVE PSYCHOLOGY, 1974, 6 (03) :325-356
[2]   Image representations for visual learning [J].
Beymer, D ;
Poggio, T .
SCIENCE, 1996, 272 (5270) :1905-1909
[3]   VIEWPOINT-DEPENDENT MECHANISMS IN VISUAL OBJECT RECOGNITION - REPLY TO TARR AND BULTHOFF (1995) [J].
BIEDERMAN, I ;
GERHARDSTEIN, PC .
JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE, 1995, 21 (06) :1506-1514
[4]   EVIDENCE FOR COMPLETE TRANSLATIONAL AND REFLECTIONAL INVARIANCE IN VISUAL OBJECT PRIMING [J].
BIEDERMAN, I ;
COOPER, EE .
PERCEPTION, 1991, 20 (05) :585-593
[5]   RECOGNITION-BY-COMPONENTS - A THEORY OF HUMAN IMAGE UNDERSTANDING [J].
BIEDERMAN, I .
PSYCHOLOGICAL REVIEW, 1987, 94 (02) :115-147
[6]   RECOGNIZING DEPTH-ROTATED OBJECTS - EVIDENCE AND CONDITIONS FOR 3-DIMENSIONAL VIEWPOINT INVARIANCE [J].
BIEDERMAN, I ;
GERHARDSTEIN, PC .
JOURNAL OF EXPERIMENTAL PSYCHOLOGY-HUMAN PERCEPTION AND PERFORMANCE, 1993, 19 (06) :1162-1182
[7]   HOW SHALL A THING BE CALLED [J].
BROWN, R .
PSYCHOLOGICAL REVIEW, 1958, 65 (01) :14-21
[8]   PSYCHOPHYSICAL SUPPORT FOR A 2-DIMENSIONAL VIEW INTERPOLATION THEORY OF OBJECT RECOGNITION [J].
BULTHOFF, HH ;
EDELMAN, S .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1992, 89 (01) :60-64
[9]   HOW ARE 3-DIMENSIONAL OBJECTS REPRESENTED IN THE BRAIN [J].
BULTHOFF, HH ;
EDELMAN, SY ;
TARR, MJ .
CEREBRAL CORTEX, 1995, 5 (03) :247-260
[10]   MENTAL ROTATION, MENTAL REPRESENTATION, AND FLAT SLOPES [J].
COHEN, D ;
KUBOVY, M .
COGNITIVE PSYCHOLOGY, 1993, 25 (03) :351-382