All Vehicles Are Cars: Subclass Preferences in Container Concepts D. T. J. Vreeswijk, K. E. A. van de Sande, C. G. M. Snoek, A. W. M. Smeulders In ACM International Conference on Multimedia Retrieval 2012. [bibtex] [pdf] [url]

This paper investigates the natural bias humans display when labeling images with a container label like vehicle or carnivore. Using three container concepts as subtree root nodes, and all available concepts between these roots and the images from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset, we analyze the differences between the images labeled at these varying levels of abstraction and the union of their constituting leaf nodes. We find that for many container concepts, a strong preference for one or a few different constituting leaf nodes occurs. These results indicate that care is needed when using hierarchical knowledge in image classification: if the aim is to classify vehicles the way humans do, then cars and buses may be the only correct results.

@InProceedings{VreeswijkICMR2012,
  author       = "Vreeswijk, D. T. J. and van de Sande, K. E. A. and Snoek, C. G. M. and Smeulders, A. W. M.",
  title        = "All Vehicles Are Cars: Subclass Preferences in Container Concepts",
  booktitle    = "ACM International Conference on Multimedia Retrieval",
  year         = "2012",
  url          = "https://ivi.fnwi.uva.nl/isis/publications/2012/VreeswijkICMR2012",
  pdf          = "https://ivi.fnwi.uva.nl/isis/publications/2012/VreeswijkICMR2012/VreeswijkICMR2012.pdf",
  has_image    = 1
}