Frequency Disentangled Residual Network
release_hiu5boclhrgopb3bx4w7wzmv4a
by
Satya Rajendra Singh, Roshan Reddy Yedla, Shiv Ram Dubey, Rakesh Sanodiya, Wei-Ta Chu
2022
Abstract
Residual networks (ResNets) have been utilized for various computer vision
and image processing applications. The residual connection improves the
training of the network with better gradient flow. A residual block consists of
few convolutional layers having trainable parameters, which leads to
overfitting. Moreover, the present residual networks are not able to utilize
the high and low frequency information suitably, which also challenges the
generalization capability of the network. In this paper, a frequency
disentangled residual network (FDResNet) is proposed to tackle these issues.
Specifically, FDResNet includes separate connections in the residual block for
low and high frequency components, respectively. Basically, the proposed model
disentangles the low and high frequency components to increase the
generalization ability. Moreover, the computation of low and high frequency
components using fixed filters further avoids the overfitting. The proposed
model is tested on benchmark CIFAR10/100, Caltech and TinyImageNet datasets for
image classification. The performance of the proposed model is also tested in
image retrieval framework. It is noticed that the proposed model outperforms
its counterpart residual model. The effect of kernel size and standard
deviation is also evaluated. The impact of the frequency disentangling is also
analyzed using saliency map.
In text/plain
format
Archived Files and Locations
application/pdf 1.0 MB
file_spci7mjuinek5eamgz5ll5h7du
|
arxiv.org (repository) web.archive.org (webarchive) |
2109.12556v2
access all versions, variants, and formats of this works (eg, pre-prints)