TY - GEN
T1 - Batch-incremental triplet sampling for training triplet networks using Bayesian updating theorem
AU - Sikaroudi, Milad
AU - Ghojogh, Benyamin
AU - Karray, Fakhri
AU - Crowley, Mark
AU - Tizhoosh, H. R.
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2020
Y1 - 2020
N2 - Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the extreme distances between instances, and some others make use of sampling. However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information. In this work, we sample triplets from distributions of data rather than from existing instances. We consider a multivariate normal distribution for the embedding of each class. Using Bayesian updating and conjugate priors, we update the distributions of classes dynamically by receiving the new mini-batches of training data. The proposed triplet mining with Bayesian updating can be used with any triplet-based loss function, e.g., triplet-loss or Neighborhood Component Analysis (NCA) loss. Accordingly, Our triplet mining approaches are called Bayesian Updating Triplet (BUT) and Bayesian Updating NCA (BUNCA), depending on which loss function is being used. Experimental results on two public datasets, namely MNIST and histopathology colorectal cancer (CRC), substantiate the effectiveness of the proposed triplet mining method.
AB - Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable training triplets. Some of these mining methods rely on the extreme distances between instances, and some others make use of sampling. However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information. In this work, we sample triplets from distributions of data rather than from existing instances. We consider a multivariate normal distribution for the embedding of each class. Using Bayesian updating and conjugate priors, we update the distributions of classes dynamically by receiving the new mini-batches of training data. The proposed triplet mining with Bayesian updating can be used with any triplet-based loss function, e.g., triplet-loss or Neighborhood Component Analysis (NCA) loss. Accordingly, Our triplet mining approaches are called Bayesian Updating Triplet (BUT) and Bayesian Updating NCA (BUNCA), depending on which loss function is being used. Experimental results on two public datasets, namely MNIST and histopathology colorectal cancer (CRC), substantiate the effectiveness of the proposed triplet mining method.
UR - http://www.scopus.com/inward/record.url?scp=85110549644&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110549644&partnerID=8YFLogxK
U2 - 10.1109/ICPR48806.2021.9412478
DO - 10.1109/ICPR48806.2021.9412478
M3 - Conference contribution
AN - SCOPUS:85110549644
T3 - Proceedings - International Conference on Pattern Recognition
SP - 7080
EP - 7086
BT - Proceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 25th International Conference on Pattern Recognition, ICPR 2020
Y2 - 10 January 2021 through 15 January 2021
ER -