TY - GEN
T1 - Large scale similarity learning using similar pairs for person verification
AU - Yang, Yang
AU - Liao, Shengcai
AU - Lei, Zhen
AU - Li, Stan Z.
N1 - Publisher Copyright:
© 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2016
Y1 - 2016
N2 - In this paper, we propose a novel similarity measure and then introduce an efficient strategy to learn it by using only similar pairs for person verification. Unlike existing metric learning methods, we consider both the difference and commonness of an image pair to increase its discriminativeness. Under a pairconstrained Gaussian assumption, we show how to obtain the Gaussian priors (i.e., corresponding covariance matrices) of dissimilar pairs from those of similar pairs. The application of a log likelihood ratio makes the learning process simple and fast and thus scalable to large datasets. Additionally, our method is able to handle heterogeneous data well. Results on the challenging datasets of face verification (LFW and Pub- Fig) and person re-identification (VIPeR) show that our algorithm outperforms the state-of-The-Art methods.
AB - In this paper, we propose a novel similarity measure and then introduce an efficient strategy to learn it by using only similar pairs for person verification. Unlike existing metric learning methods, we consider both the difference and commonness of an image pair to increase its discriminativeness. Under a pairconstrained Gaussian assumption, we show how to obtain the Gaussian priors (i.e., corresponding covariance matrices) of dissimilar pairs from those of similar pairs. The application of a log likelihood ratio makes the learning process simple and fast and thus scalable to large datasets. Additionally, our method is able to handle heterogeneous data well. Results on the challenging datasets of face verification (LFW and Pub- Fig) and person re-identification (VIPeR) show that our algorithm outperforms the state-of-The-Art methods.
UR - http://www.scopus.com/inward/record.url?scp=85007271203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007271203&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85007271203
T3 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
SP - 3655
EP - 3661
BT - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
PB - AAAI press
T2 - 30th AAAI Conference on Artificial Intelligence, AAAI 2016
Y2 - 12 February 2016 through 17 February 2016
ER -