TY - GEN
T1 - Image retrieval and classification using local distance functions
AU - Frome, Andrea
AU - Singer, Yoram
AU - Malik, Jitendra
PY - 2007
Y1 - 2007
N2 - In this paper we introduce and experiment with a framework for learning local perceptual distance functions for visual recognition. We learn a distance function for each training image as a combination of elementary distances between patch-based visual features. We apply these combined local distance functions to the tasks of image retrieval and classification of novel images. On the Caltech 101 object recognition benchmark, we achieve 60.3% mean recognition across classes using 15 training images per class, which is better than the best published performance by Zhang, et al.
AB - In this paper we introduce and experiment with a framework for learning local perceptual distance functions for visual recognition. We learn a distance function for each training image as a combination of elementary distances between patch-based visual features. We apply these combined local distance functions to the tasks of image retrieval and classification of novel images. On the Caltech 101 object recognition benchmark, we achieve 60.3% mean recognition across classes using 15 training images per class, which is better than the best published performance by Zhang, et al.
UR - http://www.scopus.com/inward/record.url?scp=84864031890&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864031890&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84864031890
SN - 9780262195683
T3 - Advances in Neural Information Processing Systems
SP - 417
EP - 424
BT - Advances in Neural Information Processing Systems 19 - Proceedings of the 2006 Conference
T2 - 20th Annual Conference on Neural Information Processing Systems, NIPS 2006
Y2 - 4 December 2006 through 7 December 2006
ER -