The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes
Most psychophysical studies of object recognition have focussed on the recognition and representation of individual objects subjects had previously explicitely been trained on. Correspondingly, modeling studies have often employed a 'grandmother'-type representation where the objects to be...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Online Access: | http://hdl.handle.net/1721.1/7222 |
| _version_ | 1826205974393782272 |
|---|---|
| author | Riesenhuber, Maximilian Poggio, Tomaso |
| author_facet | Riesenhuber, Maximilian Poggio, Tomaso |
| author_sort | Riesenhuber, Maximilian |
| collection | MIT |
| description | Most psychophysical studies of object recognition have focussed on the recognition and representation of individual objects subjects had previously explicitely been trained on. Correspondingly, modeling studies have often employed a 'grandmother'-type representation where the objects to be recognized were represented by individual units. However, objects in the natural world are commonly members of a class containing a number of visually similar objects, such as faces, for which physiology studies have provided support for a representation based on a sparse population code, which permits generalization from the learned exemplars to novel objects of that class. In this paper, we present results from psychophysical and modeling studies intended to investigate object recognition in natural ('continuous') object classes. In two experiments, subjects were trained to perform subordinate level discrimination in a continuous object class - images of computer-rendered cars - created using a 3D morphing system. By comparing the recognition performance of trained and untrained subjects we could estimate the effects of viewpoint-specific training and infer properties of the object class-specific representation learned as a result of training. We then compared the experimental findings to simulations, building on our recently presented HMAX model of object recognition in cortex, to investigate the computational properties of a population-based object class representation as outlined above. We find experimental evidence, supported by modeling results, that training builds a viewpoint- and class-specific representation that supplements a pre-existing repre-sentation with lower shape discriminability but possibly greater viewpoint invariance. |
| first_indexed | 2024-09-23T13:22:01Z |
| id | mit-1721.1/7222 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:22:01Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72222019-04-10T11:52:47Z The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes Riesenhuber, Maximilian Poggio, Tomaso Most psychophysical studies of object recognition have focussed on the recognition and representation of individual objects subjects had previously explicitely been trained on. Correspondingly, modeling studies have often employed a 'grandmother'-type representation where the objects to be recognized were represented by individual units. However, objects in the natural world are commonly members of a class containing a number of visually similar objects, such as faces, for which physiology studies have provided support for a representation based on a sparse population code, which permits generalization from the learned exemplars to novel objects of that class. In this paper, we present results from psychophysical and modeling studies intended to investigate object recognition in natural ('continuous') object classes. In two experiments, subjects were trained to perform subordinate level discrimination in a continuous object class - images of computer-rendered cars - created using a 3D morphing system. By comparing the recognition performance of trained and untrained subjects we could estimate the effects of viewpoint-specific training and infer properties of the object class-specific representation learned as a result of training. We then compared the experimental findings to simulations, building on our recently presented HMAX model of object recognition in cortex, to investigate the computational properties of a population-based object class representation as outlined above. We find experimental evidence, supported by modeling results, that training builds a viewpoint- and class-specific representation that supplements a pre-existing repre-sentation with lower shape discriminability but possibly greater viewpoint invariance. 2004-10-20T20:50:13Z 2004-10-20T20:50:13Z 2000-05-01 AIM-1682 CBCL-185 http://hdl.handle.net/1721.1/7222 en_US AIM-1682 CBCL-185 4110034 bytes 1392514 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | Riesenhuber, Maximilian Poggio, Tomaso The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title | The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title_full | The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title_fullStr | The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title_full_unstemmed | The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title_short | The Individual is Nothing, the Class Everything: Psychophysics and Modeling of Recognition in Obect Classes |
| title_sort | individual is nothing the class everything psychophysics and modeling of recognition in obect classes |
| url | http://hdl.handle.net/1721.1/7222 |
| work_keys_str_mv | AT riesenhubermaximilian theindividualisnothingtheclasseverythingpsychophysicsandmodelingofrecognitioninobectclasses AT poggiotomaso theindividualisnothingtheclasseverythingpsychophysicsandmodelingofrecognitioninobectclasses AT riesenhubermaximilian individualisnothingtheclasseverythingpsychophysicsandmodelingofrecognitioninobectclasses AT poggiotomaso individualisnothingtheclasseverythingpsychophysicsandmodelingofrecognitioninobectclasses |