Abstract
Despite great effectiveness of very deep and wide Con-
volutional Neural Networks(CNNs)in various computer vi-
sion tasks,the significant cost in terms of storage require-
ment of such networks impedes the deployment on compu-
tationally limited devices.In this paper,we propose new
modulated convolutional networks(MCNs)to improve the
portability of CNNs via binarized filters.In MCNs,we pro-
pose a new loss function which considers the filter loss,
center loss and softmax loss in an end-to-end framework.
We first introduce modulation filters(M-Filters)to recover
the unbinarized filters,which leads to a new architecture to
calculate the network model.The convolution operation is
further appro.ximated by considering intra-class compact-
ness in the loss function.As a result,our MCNs can reduce
the size of required storage space of convolutional filters
by a factor of 32,in contrast to the fuull-precision model,
while achieving much better performances than state-of
the-art binarized models.Most importantly,MCNs achieve
a comparable performance to the fiull-precision Resnets and
WideResnets.The code will be available publicly soon.