Cross-dataset transfer learning is an important problem in person re-identification (Re-ID). Unfortunately, not too many deep transfer Re-ID models exist for realistic settings of practical Re-ID systems. We propose a purely deep transfer Re-ID model consisting of a deep convolutional neural network and an autoencoder. The latent code is divided into metric embedding and nuisance variables. We then utilize an unsupervised training method that does not rely on co-training with non-deep models. Our experiments show improvements over both the baseline and competitors' transfer learning models.
@article{arxiv.1807.10591,
title = {Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning},
author = {Alexey Potapov and Sergey Rodionov and Hugo Latapie and Enzo Fenoglio},
journal= {arXiv preprint arXiv:1807.10591},
year = {2018}
}
Comments
ICANN 2018 (The 27th International Conference on Artificial Neural Networks) proceeding