TY - JOUR
T1 - Fragment-Based Learning of Visual Object Categories
AU - Hegdé, Jay
AU - Bart, Evgeniy
AU - Kersten, Daniel
N1 - Funding Information:
This work was supported by ONR grant N00014-05-1-0124 to D.K. and by NEI grant R01 EY017835. E.B. was a postdoctoral associate at the Institute of Mathematics and its Applications, University of Minnesota, during parts of this work. We thank Dr. Sharon Jansa, Dr. Norman Johnson, Dr. Paul Schrater and Mr. Peter Battaglia for helpful advice and discussions.
PY - 2008/4/22
Y1 - 2008/4/22
N2 - When we perceive a visual object, we implicitly or explicitly associate it with a category we know [1-3]. It is known that the visual system can use local, informative image fragments of a given object, rather than the whole object, to classify it into a familiar category [4-8]. How we acquire informative fragments has remained unclear. Here, we show that human observers acquire informative fragments during the initial learning of categories. We created new, but naturalistic, classes of visual objects by using a novel "virtual phylogenesis" (VP) algorithm that simulates key aspects of how biological categories evolve. Subjects were trained to distinguish two of these classes by using whole exemplar objects, not fragments. We hypothesized that if the visual system learns informative object fragments during category learning, then subjects must be able to perform the newly learned categorization by using only the fragments as opposed to whole objects. We found that subjects were able to successfully perform the classification task by using each of the informative fragments by itself, but not by using any of the comparable, but uninformative, fragments. Our results not only reveal that novel categories can be learned by discovering informative fragments but also introduce and illustrate the use of VP as a versatile tool for category-learning research.
AB - When we perceive a visual object, we implicitly or explicitly associate it with a category we know [1-3]. It is known that the visual system can use local, informative image fragments of a given object, rather than the whole object, to classify it into a familiar category [4-8]. How we acquire informative fragments has remained unclear. Here, we show that human observers acquire informative fragments during the initial learning of categories. We created new, but naturalistic, classes of visual objects by using a novel "virtual phylogenesis" (VP) algorithm that simulates key aspects of how biological categories evolve. Subjects were trained to distinguish two of these classes by using whole exemplar objects, not fragments. We hypothesized that if the visual system learns informative object fragments during category learning, then subjects must be able to perform the newly learned categorization by using only the fragments as opposed to whole objects. We found that subjects were able to successfully perform the classification task by using each of the informative fragments by itself, but not by using any of the comparable, but uninformative, fragments. Our results not only reveal that novel categories can be learned by discovering informative fragments but also introduce and illustrate the use of VP as a versatile tool for category-learning research.
KW - SYSNEURO
UR - http://www.scopus.com/inward/record.url?scp=42049109936&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=42049109936&partnerID=8YFLogxK
U2 - 10.1016/j.cub.2008.03.058
DO - 10.1016/j.cub.2008.03.058
M3 - Article
C2 - 18424145
AN - SCOPUS:42049109936
SN - 0960-9822
VL - 18
SP - 597
EP - 601
JO - Current Biology
JF - Current Biology
IS - 8
ER -