Inferring Image Templates from Classification Decisions

Dhua, Arnab; Cutzu, Florin

Inferring Image Templates from Classification Decisions

Download BibTeX Cite

Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence. Pages 1446-1450.

Abstract

Assuming human image classification decisions are based on estimating the degree of match between a small number of stored internal templates and certain regions of the input images, we present an algorithm which infers observers classification templates from their classification decisions on a set of test images. The problem is formulated as learning prototypes from labeled data under an adjustable, prototype-specific elliptical metric. The matrix of the elliptical metric indicates the pixels that the template responds to. The model was applied to human psychophysical data collected in a simple image classification experiment.

Arnab Dhua, and Florin Cutzu. 2005. Inferring Image Templates from Classification Decisions. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05. IJCAI, 1446–1450. https://ijcai.org/proceedings/2005/183

@inproceedings{ijcai2005p183,
  title     = {Inferring Image Templates from Classification Decisions},
  author    = {Dhua, Arnab and Cutzu, Florin},
  booktitle = {Proceedings of the Nineteenth International Joint Conference on
               Artificial Intelligence, {IJCAI-05}},
  publisher = {International Joint Conferences on Artificial Intelligence},
  pages     = {1446--1450},
  year      = {2005},
  url       = {https://ijcai.org/proceedings/2005/183},
}

TY  - CPAPER
TI  - Inferring Image Templates from Classification Decisions
AU  - Dhua, Arnab
AU  - Cutzu, Florin
T2  - Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, IJCAI-05
PB  - International Joint Conferences on Artificial Intelligence
PY  - 2005
SP  - 1446
EP  - 1450
UR  - https://ijcai.org/proceedings/2005/183
ER  -