Reading group on the work "Domain-Adversarial Training of Neural Networks"
(JMLR
2016) by Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H.,
Laviolette, F., Marchand, M. and Lempitsky, V.

Video conference link: https://feectu.zoom.us/j/97831236568
Instructions: http://cmp.felk.cvut.cz/~toliageo/rg/instructions.html

We will present and discuss the first deep learning approach for domain
adaptation with an adversarial scheme. It is inspired by and aligned with the
theory on domain adaptation. Despite the adversarial setup, the proposed method
enjoys simplicity and is dealing with minimization of a single loss.

Paper abstract: We introduce a new representation learning approach for domain
adaptation, in which data at training and test time come from similar but
different distributions. Our approach is directly inspired by the theory on
domain adaptation suggesting that, for effective domain transfer to be
achieved,
predictions must be made based on features that cannot discriminate between the
training (source) and test (target) domains. The approach implements this idea
in the context of neural network architectures that are trained on labeled data
from the source domain and unlabeled data from the target domain (no labeled
target-domain data is necessary). As the training progresses, the approach
promotes the emergence of features that are (i) discriminative for the main
learning task on the source domain and (ii) indiscriminate with respect to the
shift between the domains. We show that this adaptation behaviour can be
achieved in almost any feed-forward model by augmenting it with few standard
layers and a new gradient reversal layer. The resulting augmented architecture
can be trained using standard backpropagation and stochastic gradient descent,
and can thus be implemented with little effort using any of the deep learning
packages. We demonstrate the success of our approach for two distinct
classification problems (document sentiment analysis and image classification),
where state-of-the-art domain adaptation performance on standard benchmarks is
achieved. We also validate the approach for descriptor learning task in the
context of person re-identification application.

Journal paper URL: https://www.jmlr.org/papers/volume17/15-239/15-239.pdf
Conference paper URL: http://proceedings.mlr.press/v37/ganin15.html

Instructions for participants: The reading group studies the literature in the
field of pattern recognition and computer vision. At each meeting one or more
papers are prepared for presentation by a single person, the presenter. The
meetings are open to anyone, disregarding their background. It is assumed that
everyone attending the reading group has, at least briefly, read the paper –
not necessarily understanding everything. Attendants should preferably send
questions about the unclear parts to the speaker at least one day in advance.
During the presentation we aim to have a fruitful discussion, a critical
analysis of the paper, as well as brainstorming for creative extensions.

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