Permuted AdaIN: Enhancing the Representation of Local Cues in Image Classifiers
release_deqjalqmtzbxte4qqix7q5fzzu
by
Oren Nuriel, Sagie Benaim, Lior Wolf
2020
Abstract
Recent work has shown that convolutional neural network classifiers overly
rely on texture at the expense of shape cues, which adversely affects the
classifier's performance in shifted domains. In this work, we make a similar
but different distinction between local image cues, including shape and
texture, and global image statistics. We provide a method that enhances the
representation of local cues in the hidden layers of image classifiers. Our
method, called Permuted Adaptive Instance Normalization (pAdaIN), samples a
random permutation π that rearranges the samples in a given batch. Adaptive
Instance Normalization (AdaIN) is then applied between the activations of each
(non-permuted) sample i and the corresponding activations of the sample
π(i), thus swapping statistics between the samples of the batch. Since the
global image statistics are distorted, this swapping procedure causes the
network to rely on the local image cues. By choosing the random permutation
with probability p and the identity permutation otherwise, one can control
the strength of this effect. With the correct choice of p, selected without
considering the test data, our method consistently outperforms baseline methods
in image classification, as well as in the setting of domain generalization.
In text/plain
format
Archived Files and Locations
application/pdf 2.2 MB
file_3kp2mqshhja7tfb23qwsftkzui
|
arxiv.org (repository) web.archive.org (webarchive) |
2010.05785v1
access all versions, variants, and formats of this works (eg, pre-prints)