Learning similarity functions between image pairs with deep neural networks
yields highly correlated activations of embeddings. In this work, we show how
to
improve the robustness of such embeddings by exploiting the independence within
ensembles. To this end, we divide the last embedding layer of a deep network
into an embedding ensemble and formulate training this ensemble as an online
gradient boosting problem. Each learner receives a reweighted training sample
from the previous learners. Further, we propose two loss functions which
increase the diversity in our ensemble. These loss functions can be applied
either for weight initialization or during training. Together, our
contributions
leverage large embedding sizes more effectively by significantly reducing
correlation of the embedding and consequently increase retrieval accuracy of
the
embedding. Our method works with any differentiable loss function and does not
introduce any additional parameters during test time. We evaluate our metric
learning method on image retrieval tasks and show that it improves over
state-of-t

Published at PAMI 2018
https://arxiv.org/pdf/1801.04815.pdf

See the page of reading groups
http://cmp.felk.cvut.cz/~toliageo/rg/index.html