Arti Bandhana presents Online Class-Incremental Continual Learning with Adversarial Shapley Value
On 2021-11-11 11:00
at https://feectu.zoom.us/j/98555944426
Online reading group on the work "Online Class-Incremental Continual Learning
with Adversarial Shapley Value", AAAI 2021
Paper abstract: As image-based deep learning becomes pervasive on every device
from cell phones to smart watches, there is a growing need to develop methods
that continually learn from data while minimizing memory footprint and power
consumption. While memory replay techniques have shown exceptional promise for
this task of continual learning, the best method for selecting which buffered
images to replay is still an open question. In this paper, we specifically
focus
on the online class-incremental setting where a model needs to learn new
classes
continually from an online data stream. To this end, we contribute a novel
Adversarial Shapley value scoring method that scores memory data samples
according to their ability to preserve latent decision boundaries for
previously
observed classes (to maintain learning stability and avoid forgetting) while
interfering with latent decision boundaries of current classes being learned
(to
encourage plasticity and optimal learning of new class boundaries). Overall, we
observe that our proposed ASER method provides competitive or improved
performance compared to state-of-the-art replaybased continual learning methods
on a variety of datasets.
Paper url: https://www.aaai.org/AAAI21Papers/AAAI-9988.ShimD.pdf
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
with Adversarial Shapley Value", AAAI 2021
Paper abstract: As image-based deep learning becomes pervasive on every device
from cell phones to smart watches, there is a growing need to develop methods
that continually learn from data while minimizing memory footprint and power
consumption. While memory replay techniques have shown exceptional promise for
this task of continual learning, the best method for selecting which buffered
images to replay is still an open question. In this paper, we specifically
focus
on the online class-incremental setting where a model needs to learn new
classes
continually from an online data stream. To this end, we contribute a novel
Adversarial Shapley value scoring method that scores memory data samples
according to their ability to preserve latent decision boundaries for
previously
observed classes (to maintain learning stability and avoid forgetting) while
interfering with latent decision boundaries of current classes being learned
(to
encourage plasticity and optimal learning of new class boundaries). Overall, we
observe that our proposed ASER method provides competitive or improved
performance compared to state-of-the-art replaybased continual learning methods
on a variety of datasets.
Paper url: https://www.aaai.org/AAAI21Papers/AAAI-9988.ShimD.pdf
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