TY - GEN
T1 - Zero shot deep learning from semantic attributes
AU - Burlina, Philippe M.
AU - Schmidt, Aurora C.
AU - Wang, I. Jeng
PY - 2016/3/2
Y1 - 2016/3/2
N2 - We study the problem of classifying images when no training exemplars are available for some image classes, and therefore direct classification is not possible. We use instead semantic attributes: if attributes of yet unseen classes can be determined, then class labels may themselves be decided based on prior knowledge of class to attributes relationships. We present several methods for determining attributes, including (A) an approach based on attribute classifiers, and approaches using (B) MAP and (C) MMSE attribute estimators using image classifiers for known classes. Preliminary tests obtained using a dataset comprised of ImageNet images and Human218 attributes yield encouraging performance.
AB - We study the problem of classifying images when no training exemplars are available for some image classes, and therefore direct classification is not possible. We use instead semantic attributes: if attributes of yet unseen classes can be determined, then class labels may themselves be decided based on prior knowledge of class to attributes relationships. We present several methods for determining attributes, including (A) an approach based on attribute classifiers, and approaches using (B) MAP and (C) MMSE attribute estimators using image classifiers for known classes. Preliminary tests obtained using a dataset comprised of ImageNet images and Human218 attributes yield encouraging performance.
UR - http://www.scopus.com/inward/record.url?scp=84969674090&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84969674090&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2015.140
DO - 10.1109/ICMLA.2015.140
M3 - Conference contribution
AN - SCOPUS:84969674090
T3 - Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
SP - 871
EP - 876
BT - Proceedings - 2015 IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE 14th International Conference on Machine Learning and Applications, ICMLA 2015
Y2 - 9 December 2015 through 11 December 2015
ER -