Modulated Convolutional Networks

Baochang Zhang, Runqi Wang, Xiaodi Wang, Jungong Han, Rongrong Ji

Allbwn ymchwil: Cyfraniad at gyfnodolynErthygladolygiad gan gymheiriaid

6 Dyfyniadau (Scopus)
239 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

While the deep convolutional neural network (DCNN) has achieved overwhelming success in various vision tasks, its heavy computational and storage overhead hinders the practical use of resource-constrained devices. Recently, compressing DCNN models has attracted increasing attention, where binarization-based schemes have generated great research popularity due to their high compression rate. In this article, we propose modulated convolutional networks (MCNs) to obtain binarized DCNNs with high performance. We lead a new architecture in MCNs to efficiently fuse the multiple features and achieve a similar performance as the full-precision model. The calculation of MCNs is theoretically reformulated as a discrete optimization problem to build binarized DCNNs, for the first time, which jointly consider the filter loss, center loss, and softmax loss in a unified framework. Our MCNs are generic and can decompose full-precision filters in DCNNs, e.g., conventional DCNNs, VGG, AlexNet, ResNets, or Wide-ResNets, into a compact set of binarized filters which are optimized based on a projection function and a new updated rule during the backpropagation. Moreover, we propose modulation filters (M-Filters) to recover filters from binarized ones, which lead to a specific architecture to calculate the network model. Our proposed MCNs substantially reduce the storage cost of convolutional filters by a factor of 32 with a comparable performance to the full-precision counterparts, achieving much better performance than other state-of-the-art binarized models.
Iaith wreiddiolSaesneg
Nifer y tudalennau14
CyfnodolynIEEE Transactions on Neural Networks and Learning Systems
Dyddiad ar-lein cynnar09 Maw 2021
Dynodwyr Gwrthrych Digidol (DOIs)
StatwsE-gyhoeddi cyn argraffu - 09 Maw 2021

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'Modulated Convolutional Networks'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn